© 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. 7505
    Prev
    Next
    INDEX
    Explanations

    locations or environments and descriptions of actions and conditions

    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
    393
    +0.14
    0.7%
    362
    +0.13
    0.7%
    167
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.10
    393
    +0.13
    0.07
    636
    +0.10
    0.06
    Negative Logits
    SPONSORED
    -0.87
    then
    -0.67
    fully
    -0.67
    lessly
    -0.66
    isin
    -0.66
     indefinitely
    -0.64
    lvl
    -0.64
    cum
    -0.63
    owned
    -0.61
    aneously
    -0.61
    POSITIVE LOGITS
     proverbial
    1.18
     devil
    0.83
     worst
    0.75
     spotlight
    0.74
     rest
    0.73
     basics
    0.73
     simplest
    0.73
     wrong
    0.72
     glory
    0.72
     same
    0.72
    Activations Density 0.351%

    No Known Activations