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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 1061
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    481
    +0.11
    0.5%
    278
    +0.11
    0.5%
    108
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.11
    0.13
    551
    +0.11
    0.12
    718
    +0.10
    0.12
    Negative Logits
     Pigs
    -0.77
    steel
    -0.64
    arine
    -0.64
     tomorrow
    -0.62
    pite
    -0.61
     Runs
    -0.61
    geries
    -0.60
    wake
    -0.60
    advertisement
    -0.60
    rating
    -0.60
    POSITIVE LOGITS
     embarked
    0.93
     resorted
    0.89
     ventured
    0.87
     inexpl
    0.86
     encountered
    0.82
     reverted
    0.81
     confidently
    0.81
     decided
    0.80
     quietly
    0.80
     systematically
    0.80
    Activations Density 4.123%

    No Known Activations