© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 10642
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development and code

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks related to separation and list demarcation, specifically commas

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    406
    +0.05
    0.5%
    128
    +0.05
    0.5%
    541
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.05
    0.01
    140
    +0.05
    0.01
    6
    +0.04
    0.01
    Negative Logits
    Advertisements
    -0.44
    SPONSORED
    -0.43
    ruary
    -0.39
    emouth
    -0.39
    eme
    -0.37
     GOODMAN
    -0.37
     Lastly
    -0.36
    ÄŁ
    -0.36
    teness
    -0.36
    illery
    -0.35
    POSITIVE LOGITS
     creatine
    0.32
     mutual
    0.30
     analog
    0.30
     constrained
    0.30
     glyc
    0.30
     athlet
    0.30
     cookie
    0.29
     contingency
    0.29
    apor
    0.29
     genetic
    0.28
    Activations Density 0.023%

    No Known Activations