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 1536
    5. 8-RES_FS1536-JB
    6. 1251
    Prev
    Next
    INDEX
    Explanations

    critiques or warnings in reviews

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    589
    +0.10
    0.5%
    496
    +0.10
    0.4%
    186
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    709
    +0.10
    0.08
    589
    +0.10
    0.07
    176
    +0.09
    0.05
    Negative Logits
    ©¶æ
    -0.71
    20439
    -0.70
     Guth
    -0.58
     scorp
    -0.56
     reconc
    -0.55
     princ
    -0.55
    ò
    -0.54
     citiz
    -0.52
    uster
    -0.51
    psey
    -0.51
    POSITIVE LOGITS
    ;
    0.87
    :
    0.83
    .
    0.82
    :,
    0.74
    )
    0.70
    )=(
    0.66
    ,
    0.65
    ,-
    0.65
    again
    0.64
    .,
    0.62
    Activations Density 2.284%

    No Known Activations