© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 9634
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing for and caring for others, particularly in terms of food and family

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    762
    +0.12
    0.6%
    505
    +0.12
    0.6%
    46
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.12
    0.06
    350
    +0.12
    0.05
    298
    +0.11
    0.05
    Negative Logits
     hindsight
    -0.70
    zai
    -0.69
    Pattern
    -0.68
    doi
    -0.67
    onyms
    -0.66
     ASA
    -0.64
    Inv
    -0.63
     disav
    -0.63
    ounced
    -0.63
     Trial
    -0.63
    POSITIVE LOGITS
     necessities
    1.08
     groceries
    0.98
     upkeep
    0.98
     needy
    0.95
     digestion
    0.94
     emergencies
    0.94
     meals
    0.93
     subsistence
    0.92
     sust
    0.90
     chores
    0.87
    Activations Density 0.657%

    No Known Activations