© 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. 9681
    Prev
    Next
    INDEX
    Explanations

    natural disasters and emergency situations

    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
    442
    +0.12
    0.5%
    129
    +0.10
    0.5%
    198
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.12
    0.05
    442
    +0.10
    0.05
    288
    +0.10
    0.06
    Negative Logits
    IQ
    -0.81
    duino
    -0.78
    Reviewer
    -0.77
    CHQ
    -0.74
     Patent
    -0.73
     philos
    -0.72
     Idol
    -0.71
     Socrates
    -0.71
     Token
    -0.71
     liberty
    -0.71
    POSITIVE LOGITS
     engulf
    1.06
     raged
    1.05
     rav
    1.04
     Irma
    1.04
     earthqu
    1.03
    storms
    1.01
     debris
    1.01
     caused
    1.00
     rains
    0.99
     devast
    0.98
    Activations Density 0.311%

    No Known Activations