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

    Neuronpedia

    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 24576
    9. 8-RES_FS24576-JB
    11. 24128
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and software companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    447
    +0.18
    0.8%
    398
    +0.13
    0.6%
    17
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.18
    0.05
    24
    +0.13
    0.04
    326
    +0.12
    0.04
    Negative Logits
     sympathetic
    -0.70
     customary
    -0.67
     hind
    -0.65
     saturated
    -0.64
     whipping
    -0.64
     positively
    -0.63
     ashore
    -0.62
     arsen
    -0.62
     respons
    -0.62
     carbohyd
    -0.61
    POSITIVE LOGITS
     Technologies
    1.08
     Industries
    0.91
     Studios
    0.91
     Labs
    0.90
    ®
    0.87
    âĦ¢
    0.86
     Nights
    0.85
     Productions
    0.81
    Mania
    0.81
    DX
    0.81
    Activations Density 0.197%

    No Known Activations