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 3072
    5. 8-RES_FS3072-JB
    6. 376
    Prev
    Next
    INDEX
    Explanations

    information related to age and demographic details of individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    408
    +0.14
    0.7%
    59
    +0.13
    0.6%
    302
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.14
    0.06
    59
    +0.13
    0.05
    302
    +0.09
    0.05
    Negative Logits
    mbuds
    -0.81
    headers
    -0.79
    rats
    -0.79
    kefeller
    -0.78
    ascript
    -0.78
    ooks
    -0.77
    ayers
    -0.77
    vernment
    -0.76
    Ń·
    -0.76
    RAFT
    -0.76
    POSITIVE LOGITS
     woman
    0.95
     daughter
    0.91
     Frenchman
    0.88
     Indonesian
    0.86
     female
    0.83
     son
    0.82
     boy
    0.82
     girl
    0.81
     widow
    0.81
     niece
    0.79
    Activations Density 0.514%

    No Known Activations