© 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. 18696
    Prev
    Next
    INDEX
    Explanations

    mentions of the company "Gazprom" or related terms

    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
    68
    +0.10
    0.5%
    578
    +0.10
    0.5%
    316
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.02
    288
    +0.10
    0.03
    699
    +0.10
    0.02
    Negative Logits
     Kubrick
    -0.72
     Tune
    -0.68
    ract
    -0.67
     Shank
    -0.64
    owler
    -0.64
     Columb
    -0.63
    ++++
    -0.63
     Hussein
    -0.63
     Bill
    -0.62
     Heath
    -0.62
    POSITIVE LOGITS
    daq
    1.05
    atom
    1.02
    lus
    0.95
    yss
    0.92
    ldom
    0.83
    gem
    0.83
    fter
    0.83
    rified
    0.82
    hua
    0.82
    den
    0.81
    Activations Density 0.044%

    No Known Activations