© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11829
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or events

    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
    408
    +0.11
    0.5%
    113
    +0.09
    0.4%
    448
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.11
    0.06
    765
    +0.09
    0.07
    546
    +0.09
    0.06
    Negative Logits
    thood
    -0.77
    iral
    -0.67
    anish
    -0.66
    isy
    -0.66
    eus
    -0.66
    reprene
    -0.65
    ict
    -0.64
    ãĥīãĥ©
    -0.63
    viation
    -0.62
    pb
    -0.61
    POSITIVE LOGITS
     where
    1.43
     whence
    1.25
    where
    1.14
     overlooking
    1.09
     located
    1.08
     situated
    1.02
     wherein
    1.01
     adjoining
    0.99
     adjacent
    0.99
     frequ
    0.96
    Activations Density 0.310%

    No Known Activations