© 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. 219
    Prev
    Next
    INDEX
    Explanations

    a wide variety of topics, issues, and details in extensive texts

    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
    +0.28
    1.2%
    344
    +0.12
    0.5%
    53
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.28
    0.10
    71
    +0.12
    0.06
    393
    +0.10
    0.10
    Negative Logits
    henko
    -0.81
    fter
    -0.78
    ovember
    -0.77
    vest
    -0.77
    rade
    -0.72
    uca
    -0.71
    hao
    -0.70
    few
    -0.69
    roth
    -0.68
    iva
    -0.68
    POSITIVE LOGITS
     sorts
    1.25
     different
    0.98
     ways
    0.98
     possibilities
    0.98
     facets
    0.96
     assorted
    0.94
     occasions
    0.94
    things
    0.93
     varying
    0.91
     imaginable
    0.91
    Activations Density 1.766%

    No Known Activations