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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7987
    Prev
    Next
    INDEX
    Explanations

    sports-related events such as games, matches, wins, and plays

    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
    28
    +0.13
    0.6%
    152
    +0.09
    0.4%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    28
    +0.13
    0.03
    560
    +0.09
    0.02
    290
    +0.09
    0.02
    Negative Logits
    ĨĴ
    -0.76
     Nare
    -0.72
    ħĭ
    -0.68
     Corpus
    -0.67
     millenn
    -0.65
    edIn
    -0.63
     nomine
    -0.63
     Vie
    -0.61
     affected
    -0.61
     legion
    -0.59
    POSITIVE LOGITS
    advertising
    0.96
    trade
    0.93
    everything
    0.90
    your
    0.89
    return
    0.87
    shoot
    0.87
    nothing
    0.86
    hold
    0.86
    paste
    0.86
    exec
    0.85
    Activations Density 0.024%

    No Known Activations