© 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. 10773
    Prev
    Next
    INDEX
    Explanations

    phrases related to software commands 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
    360
    +0.14
    0.5%
    52
    +0.13
    0.5%
    665
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    212
    +0.14
    0.07
    360
    +0.13
    0.08
    128
    +0.11
    0.06
    Negative Logits
     Dise
    -0.89
    ibaba
    -0.86
    cised
    -0.85
    ORGE
    -0.82
     Advice
    -0.82
     Casting
    -0.81
     Mous
    -0.80
     Completed
    -0.78
     Presidency
    -0.76
    ipel
    -0.76
    POSITIVE LOGITS
    't
    1.25
    ned
    1.01
    ning
    0.98
     bother
    0.94
    nant
    0.93
    ema
    0.91
    ct
    0.90
    uts
    0.90
    atives
    0.90
    irts
    0.89
    Activations Density 1.068%

    No Known Activations