© 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 EvalsExportsinterp-engineNEWAPI 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. 24516
    Prev
    Next
    INDEX
    Explanations

    references to political movements and campaigns

    oai_token-act-pair · gpt-4o-miniTriggered 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
    +0.17
    0.8%
    481
    +0.13
    0.6%
    575
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.17
    0.08
    288
    +0.13
    0.08
    78
    +0.10
    0.05
    Negative Logits
    verbs
    -0.66
     stere
    -0.56
     Errors
    -0.55
    istered
    -0.54
     merchants
    -0.54
     phrases
    -0.54
     fractions
    -0.53
    earned
    -0.53
    juries
    -0.52
    maxwell
    -0.52
    POSITIVE LOGITS
     someday
    1.35
     anytime
    1.04
     sometime
    0.96
     sooner
    0.94
     soon
    0.93
     ASAP
    0.92
     hereafter
    0.82
    ossier
    0.82
     conclud
    0.79
     suitable
    0.76
    Activations Density 0.539%

    No Known Activations