© 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 24576
    9. 8-RES_FS24576-JB
    11. 12483
    Prev
    Next
    INDEX
    Explanations

    technical details and specifications related to machinery or equipment

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    481
    +0.24
    1.1%
    314
    +0.13
    0.6%
    7
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.24
    0.05
    284
    +0.13
    0.05
    579
    +0.12
    0.04
    Negative Logits
     exha
    -0.73
     drying
    -0.71
     challeng
    -0.71
     favourable
    -0.71
     discouraged
    -0.71
     todd
    -0.71
     eminent
    -0.70
     customary
    -0.69
     defer
    -0.68
     nursing
    -0.68
    POSITIVE LOGITS
    phia
    1.33
    idae
    1.22
    ®
    1.15
    âĦ¢
    1.09
    tics
    1.05
    aceae
    1.05
    ulous
    1.01
    tion
    0.99
     ®
    0.96
    rics
    0.94
    Activations Density 0.220%

    No Known Activations