Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 883
    Prev
    Next
    INDEX
    Explanations

    percentages or values expressed in percentage form

    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
    163
    +0.10
    0.5%
    373
    +0.10
    0.5%
    583
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.10
    0.03
    583
    +0.10
    0.03
    238
    +0.10
    0.03
    Negative Logits
    ForgeModLoader
    -0.63
     BIOS
    -0.61
    XT
    -0.59
    ITED
    -0.58
     Sakuya
    -0.58
    GD
    -0.58
     Leilan
    -0.57
     kindly
    -0.56
    RAW
    -0.56
     Healer
    -0.55
    POSITIVE LOGITS
     cent
    1.03
     capita
    0.93
    uvian
    0.87
    secut
    0.86
    missive
    0.86
    million
    0.85
    ousand
    0.84
    tains
    0.84
    CENT
    0.84
    percent
    0.83
    Activations Density 0.015%

    No Known Activations