© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 19645
    Prev
    Next
    INDEX
    Explanations

    words related to the sport of cycling, particularly race events like the Tour de France, and certain specific names related to cycling

    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
    634
    +0.11
    0.5%
    328
    +0.10
    0.5%
    497
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.01
    659
    +0.10
    0.01
    288
    +0.10
    0.01
    Negative Logits
    ousel
    -0.77
    izont
    -0.71
    SIGN
    -0.71
    ushing
    -0.63
    igating
    -0.62
    ivered
    -0.62
    leased
    -0.61
     soluble
    -0.60
    riage
    -0.60
    rican
    -0.59
    POSITIVE LOGITS
    ophone
    1.19
    ophon
    1.12
    Sax
    0.85
    xon
    0.82
    ander
    0.81
    ony
    0.80
    xy
    0.76
    ppo
    0.76
    cliffe
    0.75
    oin
    0.75
    Activations Density 0.030%

    No Known Activations