Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 695
    Prev
    Next
    INDEX
    Explanations

    references to football competitions and clubs, especially related to the UEFA Champions League

    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
    +0.29
    1.0%
    116
    +0.17
    0.6%
    376
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.29
    0.12
    326
    +0.17
    0.09
    343
    +0.17
    0.06
    Negative Logits
    ftime
    -1.02
    kefeller
    -1.00
    duino
    -0.99
    employment
    -0.97
    ©¶æ
    -0.95
    QU
    -0.95
    eral
    -0.95
    doors
    -0.95
    encers
    -0.94
    utenberg
    -0.93
    POSITIVE LOGITS
    hip
    1.45
    hips
    1.18
     League
    1.16
     Trophy
    1.14
    ively
    1.11
    aign
    1.11
    agne
    1.04
    iors
    1.03
    ial
    1.02
     Champion
    0.98
    Activations Density 1.482%

    No Known Activations