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 24576
    5. 8-RES_FS24576-JB
    6. 8393
    Prev
    Next
    INDEX
    Explanations

    mentions of sports drafts and player selections

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    481
    +0.70
    7.4%
    87
    +0.45
    4.8%
    447
    +0.27
    2.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.70
    -0.01
    481
    +0.45
    0.19
    459
    +0.27
    0.06
    Negative Logits
    MpServer
    -0.29
    Copyright
    -0.25
    daq
    -0.25
    hra
    -0.25
     outweigh
    -0.25
     guiActiveUnfocused
    -0.25
    cigarettes
    -0.24
    isSpecialOrderable
    -0.24
     vagina
    -0.23
    viol
    -0.23
    POSITIVE LOGITS
     meanwhile
    0.23
    Ͻ
    0.23
     LW
    0.23
    ¹
    0.23
     longtime
    0.22
     similarly
    0.22
     Shore
    0.22
     altern
    0.21
     downt
    0.21
     Unch
    0.21
    Activations Density 3.925%

    No Known Activations