© 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. 9101
    Prev
    Next
    INDEX
    Explanations

    text related to policy recommendations and government actions regarding discrimination and work conditions

    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
    459
    +0.15
    0.7%
    481
    +0.14
    0.7%
    50
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.15
    -0.01
    86
    +0.14
    0.05
    459
    +0.14
    0.05
    Negative Logits
     fame
    -0.79
    death
    -0.76
    Strange
    -0.76
     weird
    -0.75
    fuck
    -0.75
     mysteriously
    -0.72
    Legend
    -0.71
     unlucky
    -0.71
     lol
    -0.71
     pissed
    -0.70
    POSITIVE LOGITS
     incentiv
    1.11
     equitable
    1.11
     interventions
    1.10
     priorit
    1.09
     initiatives
    1.07
     implementing
    1.07
     reforms
    1.05
     safeguards
    1.03
     strengthening
    1.03
     tackling
    1.03
    Activations Density 0.749%

    No Known Activations