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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 1769
    Prev
    Next
    INDEX
    Explanations

    phrases related to purposes or missions

    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
    385
    +0.11
    0.5%
    594
    +0.11
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.11
    0.12
    608
    +0.11
    0.11
    49
    +0.10
    0.09
    Negative Logits
    Plus
    -0.70
    vo
    -0.66
     Extras
    -0.65
     Charges
    -0.64
     Torn
    -0.64
    checked
    -0.64
    */
    -0.64
    pants
    -0.61
     Tanz
    -0.61
     Watts
    -0.60
    POSITIVE LOGITS
     promote
    1.02
     educate
    1.00
     maximize
    0.93
     enrich
    0.91
     empower
    0.90
     stimulate
    0.90
     reinvent
    0.90
     fulfill
    0.86
     alleviate
    0.86
     showcase
    0.86
    Activations Density 1.617%

    No Known Activations