© 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. 8084
    Prev
    Next
    INDEX
    Explanations

    JavaScript variable names and errors related to variables

    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
    201
    +0.10
    0.5%
    343
    +0.10
    0.5%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.01
    343
    +0.10
    0.02
    57
    +0.10
    0.01
    Negative Logits
    iations
    -0.92
    undai
    -0.89
    iated
    -0.86
    iation
    -0.85
    iating
    -0.85
    iator
    -0.81
    ieve
    -0.79
    ieving
    -0.78
    iever
    -0.78
    icum
    -0.78
    POSITIVE LOGITS
    ãĥ£
    0.75
     Haram
    0.74
    zzy
    0.71
     cough
    0.67
    ¦
    0.66
    @#
    0.65
    zilla
    0.64
     Fighters
    0.63
     syrup
    0.63
    bie
    0.63
    Activations Density 0.030%

    No Known Activations