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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 6144
    5. 8-RES_FS6144-JB
    6. 1802
    Prev
    Next
    INDEX
    Explanations

    descriptions of personal aspirations and desires

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    738
    +0.12
    0.5%
    459
    +0.12
    0.5%
    422
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    738
    +0.12
    0.05
    641
    +0.12
    0.07
    119
    +0.11
    0.06
    Negative Logits
    rir
    -0.71
     neglect
    -0.68
     preferring
    -0.67
     shudder
    -0.63
     mysteriously
    -0.63
     Notably
    -0.63
     agreeing
    -0.62
     curiously
    -0.62
    render
    -0.61
     declining
    -0.61
    POSITIVE LOGITS
     someday
    1.05
     ASAP
    0.83
     honest
    0.72
    anything
    0.71
    oreal
    0.70
    intendo
    0.68
     something
    0.65
    someone
    0.65
    INESS
    0.65
     somebody
    0.65
    Activations Density 1.051%

    No Known Activations