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 49152
    5. 8-RES_FS49152-JB
    6. 46117
    Prev
    Next
    INDEX
    Explanations

    words related to concentration or attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    665
    +0.14
    0.6%
    251
    +0.09
    0.4%
    501
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.14
    0.03
    624
    +0.09
    0.02
    448
    +0.09
    0.02
    Negative Logits
    OUGH
    -0.75
    named
    -0.73
    adding
    -0.68
    BIT
    -0.68
    added
    -0.66
    oho
    -0.61
    mia
    -0.61
    mx
    -0.60
    Haunted
    -0.60
    ylon
    -0.60
    POSITIVE LOGITS
    rite
    0.96
     focus
    0.86
     squarely
    0.83
     attention
    0.82
     solely
    0.82
    rals
    0.77
     Attention
    0.76
     toward
    0.75
    ivism
    0.74
     foc
    0.73
    Activations Density 0.019%

    No Known Activations