© 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. 20389
    Prev
    Next
    INDEX
    Explanations

    percentages related to polling or voting outcomes

    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
    314
    +0.16
    0.7%
    151
    +0.11
    0.5%
    132
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    115
    +0.16
    0.03
    132
    +0.11
    0.03
    507
    +0.11
    0.03
    Negative Logits
    Reviewer
    -0.85
    pmwiki
    -0.79
    endum
    -0.71
    Marginal
    -0.67
    lon
    -0.66
    qua
    -0.64
    NAS
    -0.64
    abol
    -0.64
    jan
    -0.63
    atre
    -0.62
    POSITIVE LOGITS
     inclusive
    0.97
     mph
    0.92
     percent
    0.88
     depending
    0.83
     GHz
    0.79
     inches
    0.78
     million
    0.77
     billion
    0.73
    fold
    0.73
     ages
    0.72
    Activations Density 0.062%

    No Known Activations