© 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 EvalsExportsinterp-engineNEWAPI 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. 5209
    Prev
    Next
    INDEX
    Explanations

    terms related to news articles and news consumption

    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
    140
    +0.10
    0.5%
    504
    +0.10
    0.4%
    132
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    140
    +0.10
    0.04
    132
    +0.10
    0.03
    504
    +0.09
    0.03
    Negative Logits
    ayne
    -0.72
    asse
    -0.71
     Wade
    -0.69
     Ernst
    -0.67
     Lak
    -0.67
     Reson
    -0.67
     Scher
    -0.66
    inho
    -0.65
     Hamm
    -0.65
     defective
    -0.65
    POSITIVE LOGITS
    worthy
    1.13
    feed
    1.09
    room
    1.08
    rooms
    1.06
    worthiness
    0.96
    flash
    0.96
     headlines
    0.96
    reader
    0.96
     coverage
    0.94
    orial
    0.93
    Activations Density 0.045%

    No Known Activations