© 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 12288
    9. 8-RES_FS12288-JB
    11. 9645
    Prev
    Next
    INDEX
    Explanations

    business-related terms and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    594
    +0.10
    0.5%
    496
    +0.09
    0.4%
    426
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.08
    594
    +0.09
    0.05
    331
    +0.09
    0.06
    Negative Logits
    Ïī
    -0.76
    ο
    -0.74
     âĢ¦"
    -0.70
    .","
    -0.69
    ––
    -0.69
    SPONSORED
    -0.65
     thereto
    -0.64
    âĢķ
    -0.64
    adr
    -0.63
     thereof
    -0.62
    POSITIVE LOGITS
     Facts
    1.06
     Comparison
    1.00
     Features
    0.99
     Differences
    0.99
     Details
    0.99
     Matters
    0.99
     Picks
    0.99
     Overview
    0.98
     Locations
    0.97
     Benefits
    0.97
    Activations Density 0.541%

    No Known Activations