© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 1200
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical accounts or events

    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
    481
    +0.20
    0.9%
    567
    +0.11
    0.5%
    126
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.09
    126
    +0.11
    0.04
    481
    +0.10
    0.08
    Negative Logits
    soever
    -0.97
    utterstock
    -0.65
     Shutterstock
    -0.64
     Nir
    -0.61
    lr
    -0.60
    ç¥ŀ
    -0.60
     certific
    -0.55
    advertising
    -0.55
    ģĸ
    -0.55
    Baltimore
    -0.54
    POSITIVE LOGITS
     similarities
    0.99
     discrepancy
    0.96
     discrepancies
    0.96
     irregularities
    0.89
     resemblance
    0.86
     similarity
    0.86
     importance
    0.82
     involvement
    0.80
     inconsistencies
    0.80
     differences
    0.80
    Activations Density 0.990%

    No Known Activations