© 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. 6170
    Prev
    Next
    INDEX
    Explanations

    words related to political or social issues, especially highlighting disenfranchisement and political manipulation

    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
    167
    +0.13
    0.6%
    389
    +0.12
    0.6%
    0
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.13
    0.03
    0
    +0.12
    0.03
    137
    +0.12
    0.02
    Negative Logits
     Juliet
    -0.73
     Suit
    -0.66
     Shogun
    -0.63
    OPLE
    -0.63
     drafts
    -0.61
     Goldberg
    -0.61
     Nash
    -0.61
    DragonMagazine
    -0.60
     Ground
    -0.60
     Goose
    -0.60
    POSITIVE LOGITS
    rup
    1.27
    array
    1.24
    assemb
    1.22
    organized
    1.20
    burse
    1.19
    concert
    1.18
    interested
    1.18
    ordered
    1.15
    puting
    1.14
    qus
    1.14
    Activations Density 0.013%

    No Known Activations