© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 8057
    Prev
    Next
    INDEX
    Explanations

    objects related to physical injuries or attacks

    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
    288
    +0.12
    0.6%
    711
    +0.09
    0.4%
    109
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.09
    575
    +0.09
    0.07
    711
    +0.08
    0.03
    Negative Logits
    urches
    -0.84
    nces
    -0.80
     Parties
    -0.80
    rencies
    -0.80
     acron
    -0.79
     Governments
    -0.79
     portfolios
    -0.78
    sites
    -0.78
     publications
    -0.77
     embassies
    -0.77
    POSITIVE LOGITS
    icum
    0.86
    assian
    0.78
    load
    0.78
    few
    0.77
    ogram
    0.76
    asket
    0.76
    imeter
    0.74
    plane
    0.73
    oscope
    0.73
    hole
    0.73
    Activations Density 0.488%

    No Known Activations