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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 516
    Prev
    Next
    INDEX
    Explanations

    recipe ingredients and instructions

    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
    314
    +0.15
    0.7%
    160
    +0.15
    0.7%
    640
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.15
    0.08
    160
    +0.15
    0.09
    627
    +0.14
    0.06
    Negative Logits
     bids
    -0.69
     adm
    -0.69
     Fletcher
    -0.68
     creep
    -0.68
     tender
    -0.67
     soaring
    -0.66
     accus
    -0.66
     Obi
    -0.66
     stalking
    -0.66
     glide
    -0.66
    POSITIVE LOGITS
    etc
    1.29
    Flickr
    1.17
    pmwiki
    1.11
    Accessory
    1.05
    whatever
    1.05
    ãĤ¨ãĥ«
    1.04
    articles
    1.03
    sites
    0.99
    ËĪ
    0.98
    WARN
    0.96
    Activations Density 0.676%

    No Known Activations