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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11387
    Prev
    Next
    INDEX
    Explanations

    words related to the Stanley Cup and hockey championships

    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
    725
    +0.11
    0.5%
    40
    +0.10
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.11
    0.01
    40
    +0.10
    0.01
    335
    +0.10
    0.01
    Negative Logits
    ged
    -0.98
    Reviewer
    -0.84
    gil
    -0.79
    hy
    -0.79
    eer
    -0.79
    edIn
    -0.78
    */(
    -0.76
    ging
    -0.75
    dress
    -0.75
    suit
    -0.75
    POSITIVE LOGITS
     Kubrick
    1.14
     Baldwin
    0.92
     Cup
    0.83
    thal
    0.78
     Cups
    0.78
     Bros
    0.77
     Stanley
    0.76
    lihood
    0.75
     Trophy
    0.70
     Winter
    0.70
    Activations Density 0.019%

    No Known Activations