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. 2191
    Prev
    Next
    INDEX
    Explanations

    phrases referring to daily activities or routines

    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
    79
    +0.11
    0.5%
    710
    +0.10
    0.5%
    725
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    710
    +0.11
    0.05
    725
    +0.10
    0.05
    651
    +0.10
    0.06
    Negative Logits
    lda
    -0.90
    agra
    -0.88
    holes
    -0.84
    artisan
    -0.84
    enes
    -0.79
    owitz
    -0.76
    enic
    -0.73
    IDA
    -0.71
    erala
    -0.71
    imately
    -0.71
    POSITIVE LOGITS
     occurrence
    1.13
     intervals
    1.01
    motion
    1.00
     occurrences
    0.99
     recurring
    0.99
     upkeep
    0.95
    ãĥ£
    0.95
     updates
    0.92
     flyer
    0.91
     reminders
    0.88
    Activations Density 0.664%

    No Known Activations