© 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. 18123
    Prev
    Next
    INDEX
    Explanations

    mentions of announcements or premieres

    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
    +0.15
    0.7%
    373
    +0.14
    0.6%
    185
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.15
    0.05
    346
    +0.14
    0.04
    172
    +0.10
    0.04
    Negative Logits
    NOW
    -0.74
    utf
    -0.69
     nowadays
    -0.63
     denies
    -0.62
    arta
    -0.62
    imar
    -0.61
    =-=-=-=-
    -0.60
    int
    -0.60
     shouldn
    -0.59
     someday
    -0.58
    POSITIVE LOGITS
    Reviewer
    0.79
    perty
    0.74
    USS
    0.72
     another
    0.70
     again
    0.68
    reetings
    0.64
     anew
    0.64
     abruptly
    0.63
    amorph
    0.62
    owship
    0.62
    Activations Density 0.290%

    No Known Activations