© 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. 18208
    Prev
    Next
    INDEX
    Explanations

    specific political organizations or groups

    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
    447
    +0.15
    0.7%
    481
    +0.14
    0.6%
    57
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.04
    57
    +0.14
    0.03
    146
    +0.11
    0.03
    Negative Logits
    makers
    -0.80
    abilia
    -0.76
    wagen
    -0.75
    words
    -0.74
    tainment
    -0.72
    asures
    -0.72
    icians
    -0.72
    izers
    -0.71
    lees
    -0.71
    obyl
    -0.71
    POSITIVE LOGITS
    PA
    1.00
    IL
    0.87
    CCC
    0.87
    YC
    0.85
    OC
    0.83
    ORN
    0.83
    DEF
    0.82
    ESH
    0.81
    RA
    0.81
    OR
    0.81
    Activations Density 0.065%

    No Known Activations