© 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. 7733
    Prev
    Next
    INDEX
    Explanations

    descriptions or elaborations within a text

    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
    362
    +0.14
    0.6%
    640
    +0.13
    0.6%
    131
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.14
    0.04
    362
    +0.13
    0.04
    29
    +0.12
    0.04
    Negative Logits
     lasted
    -0.87
    0000000000000000
    -0.78
     succeeded
    -0.77
    soever
    -0.77
     rocked
    -0.74
     behaved
    -0.72
     harmed
    -0.70
     bandwagon
    -0.69
     accountable
    -0.69
     hindered
    -0.68
    POSITIVE LOGITS
    effic
    1.06
     accordance
    1.04
     detail
    1.03
     conjunction
    1.02
    efficiency
    1.01
    humane
    1.01
     lieu
    0.92
     terms
    0.91
     advance
    0.91
    escap
    0.90
    Activations Density 0.140%

    No Known Activations