© 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. 11878
    Prev
    Next
    INDEX
    Explanations

    text related to legal matters, political figures, and societal issues

    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
    291
    +0.12
    0.5%
    620
    +0.11
    0.5%
    278
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.12
    0.11
    665
    +0.11
    0.13
    526
    +0.11
    -0.02
    Negative Logits
    theless
    -0.63
     clutter
    -0.63
     Fey
    -0.62
     Ballard
    -0.61
     confusion
    -0.60
     sts
    -0.59
     MFT
    -0.59
     Nek
    -0.59
     BW
    -0.58
     FTC
    -0.58
    POSITIVE LOGITS
     dearly
    0.90
    borgh
    0.75
    abouts
    0.74
    tre
    0.72
    inge
    0.72
    course
    0.71
    sed
    0.71
    ethyst
    0.70
    igraph
    0.68
    unes
    0.67
    Activations Density 3.328%

    No Known Activations