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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8915
    Prev
    Next
    INDEX
    Explanations

    news-related terms and names of specific individuals involved in political actions or 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_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
    314
    +0.13
    0.6%
    503
    +0.11
    0.5%
    725
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    725
    +0.13
    0.03
    140
    +0.11
    0.03
    744
    +0.10
    0.03
    Negative Logits
    hetti
    -0.85
     Defin
    -0.67
    regor
    -0.66
    asse
    -0.66
    pired
    -0.66
     habitable
    -0.65
     comma
    -0.65
    ength
    -0.64
    inho
    -0.62
    asus
    -0.61
    POSITIVE LOGITS
    worthy
    1.07
    reader
    1.05
    flash
    1.03
    agency
    1.01
    room
    0.99
    groups
    0.98
    worthiness
    0.97
    agent
    0.96
    group
    0.95
    conference
    0.95
    Activations Density 0.031%

    No Known Activations