© 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. 10758
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and statistics, particularly related to Detroit teams

    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
    288
    +0.19
    0.7%
    167
    +0.16
    0.6%
    527
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.10
    117
    +0.16
    0.07
    302
    +0.14
    0.07
    Negative Logits
    ntil
    -1.19
    yip
    -1.18
    sembly
    -1.14
    creen
    -1.12
    ccording
    -1.11
    thood
    -1.10
    mble
    -1.09
     Seym
    -1.06
    76561
    -1.04
    mares
    -1.02
    POSITIVE LOGITS
    shire
    1.70
     Pistons
    1.27
     Lions
    1.09
     Tigers
    1.06
    stones
    0.97
     Mercy
    0.95
    inois
    0.89
    ford
    0.89
    sburgh
    0.87
    ers
    0.86
    Activations Density 1.429%

    No Known Activations