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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 9722
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism or negativities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    366
    +0.14
    0.6%
    270
    +0.13
    0.6%
    402
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    366
    +0.14
    0.07
    402
    +0.13
    0.06
    412
    +0.10
    0.05
    Negative Logits
    tics
    -0.78
    mbuds
    -0.68
    aths
    -0.63
    borgh
    -0.62
    pherd
    -0.62
    Progress
    -0.61
    borg
    -0.61
     Contributions
    -0.60
    zai
    -0.60
    ingen
    -0.59
    POSITIVE LOGITS
     iteration
    0.97
     installment
    0.97
     batch
    0.96
     phase
    0.93
     baseman
    0.93
     tier
    0.92
     half
    0.90
     edition
    0.88
     stages
    0.87
     inning
    0.86
    Activations Density 0.146%

    No Known Activations