© 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 EvalsExportsAPI 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. 93
    Prev
    Next
    INDEX
    Explanations

    phrases related to coding practices, programming concepts and technical instructions

    oai_token-act-pair · gpt-3.5-turbo
    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
    393
    +0.25
    0.9%
    26
    +0.15
    0.6%
    603
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    706
    +0.25
    0.08
    603
    +0.15
    0.07
    26
    +0.14
    0.07
    Negative Logits
    agin
    -1.16
    rolet
    -0.92
    Lay
    -0.88
    yan
    -0.86
    endish
    -0.84
    entry
    -0.84
    gan
    -0.82
    zzi
    -0.82
    alin
    -0.80
    edly
    -0.80
    POSITIVE LOGITS
    soever
    1.67
     evaluating
    1.11
     faced
    1.11
     comparing
    1.07
     contrasted
    1.07
     confronted
    1.06
    irlf
    1.00
     viewed
    0.98
     compared
    0.97
     assessing
    0.96
    Activations Density 0.955%

    No Known Activations