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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 2414
    Prev
    Next
    INDEX
    Explanations

    information related to news articles, events, and news agencies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    211
    +0.12
    0.6%
    521
    +0.11
    0.5%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.12
    0.06
    521
    +0.11
    0.06
    257
    +0.09
    0.06
    Negative Logits
     Lilith
    -0.65
    aimon
    -0.60
     Bord
    -0.60
    oft
    -0.58
    imer
    -0.58
    iaries
    -0.57
    abal
    -0.56
    laus
    -0.56
    seek
    -0.56
    asers
    -0.55
    POSITIVE LOGITS
    interstitial
    0.97
     Invalid
    0.88
     Cancel
    0.85
    Sorry
    0.75
     Login
    0.74
    iframe
    0.73
     login
    0.72
     captcha
    0.67
     Email
    0.67
     HTML
    0.67
    Activations Density 0.543%

    No Known Activations