© 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. 10743
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic grading, scholarships, financial matters, legal disputes, health points, gaming terms, and technical specifications

    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
    41
    +0.13
    0.5%
    502
    +0.11
    0.5%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.20
    41
    +0.11
    0.09
    540
    +0.11
    0.14
    Negative Logits
    #$
    -0.72
     Brow
    -0.71
    imensional
    -0.69
    greSQL
    -0.69
    abyte
    -0.68
    rake
    -0.66
     Helpful
    -0.66
    amina
    -0.65
    ordinate
    -0.64
    igious
    -0.64
    POSITIVE LOGITS
     codes
    0.70
    plates
    0.69
    warts
    0.69
    iannopoulos
    0.66
    ="#
    0.65
    itent
    0.65
    owder
    0.65
    lance
    0.64
    ensis
    0.64
    antam
    0.63
    Activations Density 4.546%

    No Known Activations