© 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. 24130
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to written or visual content, such as articles, poems, and performances

    oai_token-act-pair · gpt-4o-miniTriggered 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
    481
    +0.23
    1.2%
    87
    +0.23
    1.1%
    447
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.10
    325
    +0.23
    0.07
    481
    +0.14
    0.08
    Negative Logits
    ccording
    -0.60
    cale
    -0.58
    iolet
    -0.54
     Westminster
    -0.54
    ADRA
    -0.54
    )=(
    -0.54
     Marketable
    -0.53
     PsyNet
    -0.52
    poon
    -0.49
    ystem
    -0.49
    POSITIVE LOGITS
     itself
    0.96
    osphere
    0.84
    ultimate
    0.82
    liest
    0.80
    iest
    0.76
    ieth
    0.75
    's
    0.67
    forts
    0.66
    hest
    0.61
    marks
    0.61
    Activations Density 0.661%

    No Known Activations