© 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. 12993
    Prev
    Next
    INDEX
    Explanations

    mentions of states in the context of political and social issues related to income, poverty, and public policy

    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
    573
    +0.12
    0.5%
    31
    +0.11
    0.5%
    497
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.12
    0.03
    121
    +0.11
    0.03
    329
    +0.10
    0.03
    Negative Logits
    DragonMagazine
    -0.97
     analys
    -0.93
     arte
    -0.79
     translator
    -0.77
     realise
    -0.77
     behavi
    -0.77
     antis
    -0.74
     apologise
    -0.72
     medi
    -0.72
     transl
    -0.72
    POSITIVE LOGITS
     Pennsylvania
    1.40
    sylvania
    1.37
    Virginia
    1.36
     Tennessee
    1.36
     Virginia
    1.36
     Louisiana
    1.35
     Kentucky
    1.34
     Idaho
    1.33
     Nevada
    1.33
     Wisconsin
    1.31
    Activations Density 0.180%

    No Known Activations