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 768
    5. 8-RES_FS768-JB
    6. 378
    Prev
    Next
    INDEX
    Explanations

    details or prompts related to newsletter sign-ups

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    373
    +0.11
    0.5%
    211
    +0.11
    0.5%
    208
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    521
    +0.11
    0.08
    373
    +0.11
    -0.07
    257
    +0.11
    0.10
    Negative Logits
    etts
    -0.69
    abal
    -0.69
    abase
    -0.64
    geist
    -0.62
     Hann
    -0.61
    gow
    -0.61
    naire
    -0.60
    âĢİ
    -0.60
    imer
    -0.60
    igans
    -0.59
    POSITIVE LOGITS
    iframe
    0.95
    interstitial
    0.94
    Subscribe
    0.81
     subscribing
    0.75
     Cancel
    0.70
    Content
    0.69
    content
    0.69
     embed
    0.68
     Email
    0.67
     Kavanaugh
    0.67
    Activations Density 3.446%

    No Known Activations