© 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. 17491
    Prev
    Next
    INDEX
    Explanations

    names of particular people related to governmental or political positions

    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
    407
    +0.11
    0.5%
    314
    +0.10
    0.5%
    9
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.06
    81
    +0.10
    0.05
    232
    +0.08
    0.05
    Negative Logits
     robbers
    -0.71
     WOM
    -0.68
     graveyard
    -0.66
     Twins
    -0.64
     vag
    -0.62
     Circus
    -0.62
     nostalg
    -0.62
     Thieves
    -0.61
     captcha
    -0.61
    ahime
    -0.60
    POSITIVE LOGITS
     Mattis
    0.82
    reet
    0.76
     Tillerson
    0.75
    asury
    0.72
     Adviser
    0.72
     Merrill
    0.71
    assadors
    0.69
     UNCLASSIFIED
    0.69
     Downing
    0.69
    Task
    0.67
    Activations Density 0.178%

    No Known Activations