© 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 49152
    9. 8-RES_FS49152-JB
    11. 37396
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or thanks

    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
    373
    +0.14
    0.7%
    262
    +0.12
    0.6%
    760
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    262
    +0.14
    0.02
    760
    +0.12
    0.01
    391
    +0.10
    0.01
    Negative Logits
    Default
    -0.67
    APD
    -0.64
    estyles
    -0.60
    Pred
    -0.58
    farious
    -0.57
     outper
    -0.57
     behavi
    -0.56
     dominates
    -0.56
     pred
    -0.56
    alth
    -0.55
    POSITIVE LOGITS
     welcome
    0.79
    !!!!!
    0.79
     gracious
    0.76
     sir
    0.76
     thank
    0.72
     kindly
    0.72
     goodbye
    0.72
     Thank
    0.71
     generous
    0.70
     hello
    0.67
    Activations Density 0.021%

    No Known Activations