© 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 12288
    9. 8-RES_FS12288-JB
    11. 1470
    Prev
    Next
    INDEX
    Explanations

    names of political figures, organizations, and terminology related to political 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_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    480
    +0.11
    0.5%
    645
    +0.10
    0.5%
    711
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    711
    +0.11
    0.04
    620
    +0.10
    0.02
    516
    +0.10
    0.06
    Negative Logits
     Billboard
    -0.60
     livestream
    -0.60
     concise
    -0.60
     screenshots
    -0.60
     archived
    -0.58
     âĢº
    -0.58
     crochet
    -0.57
     Bungie
    -0.57
     presentations
    -0.56
     Offline
    -0.56
    POSITIVE LOGITS
     whom
    0.79
     respectively
    0.78
    ."[
    0.71
     alike
    0.70
    fascist
    0.68
    .).
    0.68
    volent
    0.67
    ).[
    0.66
    .[
    0.66
    ocrats
    0.65
    Activations Density 2.157%

    No Known Activations