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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23663
    Prev
    Next
    INDEX
    Explanations

    schedule-related information, particularly regarding operating hours and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    601
    +0.09
    0.4%
    731
    +0.09
    0.4%
    372
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    677
    +0.09
    0.05
    281
    +0.09
    0.04
    601
    +0.09
    0.03
    Negative Logits
     deriv
    -0.66
    founded
    -0.66
     clone
    -0.65
     Inher
    -0.64
    abulary
    -0.63
     transpl
    -0.62
     inherited
    -0.62
    ingen
    -0.62
    cule
    -0.61
    ij士
    -0.61
    POSITIVE LOGITS
     Mondays
    1.62
     noon
    1.58
     Thurs
    1.54
     Tues
    1.51
     Saturdays
    1.50
     midnight
    1.49
     Fridays
    1.49
     midday
    1.41
     Sundays
    1.40
     curfew
    1.40
    Activations Density 0.743%

    No Known Activations