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 49152
    5. 8-RES_FS49152-JB
    6. 41258
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    469
    +0.15
    0.7%
    640
    +0.12
    0.6%
    57
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.15
    0.02
    160
    +0.12
    0.02
    469
    +0.10
    0.01
    Negative Logits
    emis
    -0.81
    inyl
    -0.75
    hement
    -0.72
    schild
    -0.69
    dor
    -0.67
    wards
    -0.67
    ettings
    -0.66
    owship
    -0.65
    oneliness
    -0.65
    ngth
    -0.65
    POSITIVE LOGITS
    Thread
    0.70
     reservation
    0.66
    à¼
    0.65
     Pastebin
    0.64
    notations
    0.63
    Narr
    0.59
    Links
    0.58
    Spoiler
    0.58
    ãĥĥãĥĪ
    0.58
    animous
    0.57
    Activations Density 0.011%

    No Known Activations