© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 37321
    Prev
    Next
    INDEX
    Explanations

    specific dates and amounts related to events or articles

    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
    630
    +0.10
    0.5%
    737
    +0.10
    0.4%
    62
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.10
    0.01
    739
    +0.10
    0.01
    241
    +0.10
    0.01
    Negative Logits
    vik
    -0.80
    andre
    -0.72
    bush
    -0.69
    erry
    -0.68
    toe
    -0.66
     Aires
    -0.65
    nown
    -0.65
    wen
    -0.65
    lif
    -0.64
    erred
    -0.64
    POSITIVE LOGITS
     Category
    0.91
     Select
    0.91
     Choose
    0.88
    Sort
    0.86
     Default
    0.79
     Sort
    0.77
    Category
    0.77
     Alabama
    0.77
     Cum
    0.76
     favorites
    0.75
    Activations Density 0.022%

    No Known Activations