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 49152
    5. 8-RES_FS49152-JB
    6. 40123
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing personal growth and development

    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
    480
    +0.37
    1.8%
    447
    +0.14
    0.7%
    481
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.37
    0.00
    351
    +0.14
    0.03
    266
    +0.13
    0.06
    Negative Logits
     Reported
    -0.84
    eligible
    -0.83
    Federal
    -0.83
     Illegal
    -0.82
    illegal
    -0.81
     ineligible
    -0.76
    uled
    -0.75
    hof
    -0.74
    bill
    -0.73
    untled
    -0.73
    POSITIVE LOGITS
     empathy
    1.21
     subconscious
    1.09
     transcend
    1.07
     insight
    1.06
     empath
    1.04
     tactile
    1.04
     meditation
    1.03
     awareness
    1.02
     intuition
    1.01
     sensory
    1.01
    Activations Density 0.576%

    No Known Activations