© 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. 8838
    Prev
    Next
    INDEX
    Explanations

    adjectives or phrases related to visual appearance and design

    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
    196
    +0.12
    0.5%
    386
    +0.11
    0.5%
    333
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    532
    +0.12
    0.02
    333
    +0.11
    0.01
    291
    +0.10
    0.02
    Negative Logits
    urdue
    -0.82
    uesday
    -0.69
    hement
    -0.68
    illet
    -0.66
    Together
    -0.65
    ycle
    -0.63
    igham
    -0.62
    jri
    -0.60
    ital
    -0.59
     improv
    -0.59
    POSITIVE LOGITS
     beh
    0.95
     ears
    0.92
    ĸļ
    0.86
     hairs
    0.85
     sockets
    0.82
    itness
    0.82
    catching
    0.79
     watering
    0.79
     eye
    0.78
     noses
    0.75
    Activations Density 0.072%

    No Known Activations