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. 436
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Louis", potentially referring to a person named Louis or various entities related to Louis such as Louis C.K. or Louis Glunz Beer

    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
    679
    +0.15
    0.7%
    376
    +0.13
    0.6%
    263
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.12
    232
    +0.13
    0.09
    659
    +0.12
    0.09
    Negative Logits
    ition
    -0.71
    TY
    -0.67
    ishment
    -0.67
    ctica
    -0.67
    ãĥĥãĥī
    -0.67
    ptive
    -0.67
     Scotia
    -0.65
    jamin
    -0.64
    thia
    -0.64
    ting
    -0.62
    POSITIVE LOGITS
    edIn
    1.28
    ĸļ
    0.91
    ean
    0.85
    ogly
    0.84
    edly
    0.83
    atile
    0.82
    isoft
    0.81
    aned
    0.80
    ed
    0.80
    eday
    0.80
    Activations Density 1.477%

    No Known Activations