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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 1428
    Prev
    Next
    INDEX
    Explanations

    statements related to legal proceedings and detailed descriptions

    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
    640
    +0.24
    1.1%
    314
    +0.14
    0.7%
    6
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.24
    0.19
    6
    +0.14
    0.14
    64
    +0.12
    -0.05
    Negative Logits
     tink
    -0.77
     estranged
    -0.70
    ensibly
    -0.69
     overth
    -0.68
     unsc
    -0.66
     diving
    -0.66
     shuff
    -0.63
     orche
    -0.63
     sailing
    -0.63
    inyl
    -0.62
    POSITIVE LOGITS
    Posted
    1.09
    Comment
    1.03
    ³³³³
    0.99
    =-=-=-=-=-=-=-=-
    0.97
    posted
    0.97
    âĶĢâĶĢâĶĢâĶĢ
    0.96
    CONCLUS
    0.94
    ONSORED
    0.93
    Narr
    0.92
    Translation
    0.92
    Activations Density 0.928%

    No Known Activations