© 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 24576
    9. 8-RES_FS24576-JB
    11. 23546
    Prev
    Next
    INDEX
    Explanations

    numeric values related to counts or quantities in sports and competitions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    71
    +0.12
    0.5%
    418
    +0.11
    0.5%
    408
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.12
    0.02
    327
    +0.11
    0.02
    418
    +0.09
    0.02
    Negative Logits
    Dialogue
    -0.78
    fw
    -0.70
    tch
    -0.69
    erb
    -0.69
    Ļ½
    -0.65
    anything
    -0.64
    eric
    -0.64
    quire
    -0.64
    potion
    -0.64
    whel
    -0.63
    POSITIVE LOGITS
     phases
    1.03
     sides
    1.00
     facets
    0.98
     corners
    0.85
     branches
    0.85
     sexes
    0.83
     occupants
    0.83
    teenth
    0.81
     seasons
    0.79
     quarters
    0.79
    Activations Density 0.036%

    No Known Activations