© 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. 7521
    Prev
    Next
    INDEX
    Explanations

    gender-related content, discussions regarding attraction, relationships, and behaviors related to social interactions

    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
    762
    +0.12
    0.5%
    575
    +0.10
    0.5%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.12
    0.08
    575
    +0.10
    0.08
    51
    +0.10
    0.06
    Negative Logits
     Canaver
    -0.68
    ASED
    -0.67
    ATIONAL
    -0.65
    DEN
    -0.64
     convergence
    -0.63
    Completed
    -0.63
    bernatorial
    -0.63
     Nun
    -0.62
    emp
    -0.62
     renaissance
    -0.59
    POSITIVE LOGITS
    hips
    1.19
    hip
    1.13
    folk
    1.10
    pace
    1.06
     alike
    1.03
    paces
    1.02
     whom
    0.96
    ystem
    0.90
     who
    0.86
    '
    0.86
    Activations Density 0.342%

    No Known Activations