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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 42858
    Prev
    Next
    INDEX
    Explanations

    mentions of financial amounts, specifically in rupees

    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
    443
    +0.12
    0.6%
    223
    +0.12
    0.5%
    385
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.12
    0.02
    223
    +0.12
    0.02
    522
    +0.11
    0.02
    Negative Logits
     Jenner
    -0.76
     Glou
    -0.74
     Pens
    -0.73
     Staten
    -0.73
     Destroyer
    -0.72
     Portsmouth
    -0.71
     Plymouth
    -0.70
     Hitman
    -0.70
    ffen
    -0.69
     Sinclair
    -0.69
    POSITIVE LOGITS
     Rs
    0.98
    500
    0.96
     crore
    0.91
    ibaba
    0.90
    600
    0.89
    300
    0.88
    400
    0.85
    800
    0.85
    200
    0.84
    750
    0.84
    Activations Density 0.007%

    No Known Activations