© 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. 8235
    Prev
    Next
    INDEX
    Explanations

    instructions for technological tasks involving software and hardware configurations

    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
    49
    +0.02
    0.4%
    577
    +0.02
    0.4%
    218
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.02
    0.04
    655
    +0.02
    0.03
    601
    +0.02
    0.02
    Negative Logits
    rums
    -0.17
    hani
    -0.15
    uno
    -0.14
    verning
    -0.14
    apego
    -0.13
    iannopoulos
    -0.13
    resh
    -0.13
     inherent
    -0.13
    naire
    -0.13
    antry
    -0.13
    POSITIVE LOGITS
    CLASSIFIED
    0.14
     readable
    0.14
    edia
    0.14
     paraph
    0.14
    Pub
    0.14
    Tank
    0.13
     bookmark
    0.13
    bilt
    0.12
    plete
    0.12
    LAB
    0.12
    Activations Density 0.202%

    No Known Activations