© 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. 5768
    Prev
    Next
    INDEX
    Explanations

    mentions of political events and issues related to government actions

    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
    447
    +0.12
    0.6%
    361
    +0.09
    0.4%
    291
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.06
    291
    +0.09
    0.04
    481
    +0.09
    0.04
    Negative Logits
    etheless
    -0.76
    saw
    -0.73
    ovember
    -0.66
    cms
    -0.63
     greets
    -0.62
    helm
    -0.57
     confir
    -0.57
    berra
    -0.56
    !.
    -0.56
     discovers
    -0.56
    POSITIVE LOGITS
     obsolete
    1.00
     moot
    0.88
    solete
    0.76
     inherently
    0.75
     bitters
    0.73
     irrelevant
    0.72
     favorably
    0.71
     appealing
    0.69
     ineffective
    0.69
     pointless
    0.68
    Activations Density 0.297%

    No Known Activations