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. 527
    Prev
    Next
    INDEX
    Explanations

    names of previous players in commentary on games

    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
    650
    +0.12
    0.5%
    65
    +0.11
    0.5%
    379
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.03
    284
    +0.11
    0.03
    406
    +0.10
    0.03
    Negative Logits
    lished
    -0.80
     kcal
    -0.74
    regor
    -0.69
    ONSORED
    -0.68
    eele
    -0.67
    è¦ļéĨĴ
    -0.66
     Mechdragon
    -0.65
     QR
    -0.62
    Gaza
    -0.61
     Cosponsors
    -0.61
    POSITIVE LOGITS
    sonian
    0.86
    ttle
    0.83
    ung
    0.83
    inge
    0.81
    azine
    0.80
    acket
    0.80
    osphere
    0.80
    inite
    0.78
    stream
    0.77
    abyte
    0.77
    Activations Density 0.190%

    No Known Activations