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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 43412
    Prev
    Next
    INDEX
    Explanations

    mentions of New York City

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    241
    +0.11
    0.5%
    219
    +0.09
    0.4%
    300
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.11
    0.02
    547
    +0.09
    0.01
    581
    +0.09
    0.01
    Negative Logits
    rar
    -0.92
    ãĥĦ
    -0.84
    ibilities
    -0.81
    terness
    -0.80
    yip
    -0.77
    ãĥ¼ãĥĨ
    -0.76
    iru
    -0.75
    gotten
    -0.74
    VALUE
    -0.73
    wcsstore
    -0.72
    POSITIVE LOGITS
     skyline
    0.97
     subway
    0.95
     streets
    0.95
    scape
    0.95
     borough
    0.94
     landmarks
    0.94
     Council
    0.91
     FC
    0.90
     neighborhoods
    0.88
     Mayor
    0.86
    Activations Density 0.022%

    No Known Activations