© 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. 9853
    Prev
    Next
    INDEX
    Explanations

    natural disasters and their aftermath

    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
    756
    +0.12
    0.6%
    1
    +0.10
    0.5%
    471
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    150
    +0.12
    0.05
    551
    +0.10
    0.06
    756
    +0.10
    -0.02
    Negative Logits
     interchangeable
    -0.79
     salsa
    -0.75
     clipboard
    -0.74
     desks
    -0.73
    ©¶æ¥µ
    -0.72
     bios
    -0.72
     Preferences
    -0.72
     Libraries
    -0.70
     nods
    -0.69
    parency
    -0.68
    POSITIVE LOGITS
     occurred
    1.23
     devast
    1.21
     raged
    1.21
     perpetrated
    1.20
     caused
    1.19
     occurring
    1.14
     inflicted
    1.14
     engulf
    1.13
     occur
    1.08
     rav
    1.07
    Activations Density 0.883%

    No Known Activations