© 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. 17560
    Prev
    Next
    INDEX
    Explanations

    mentions of specific events or items in a list-like format

    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
    575
    +0.15
    0.7%
    127
    +0.13
    0.6%
    85
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.15
    0.07
    103
    +0.13
    0.06
    254
    +0.11
    0.05
    Negative Logits
     guiName
    -0.84
     ACTIONS
    -0.71
     Solitaire
    -0.71
     scattering
    -0.67
     Farming
    -0.65
     DRAG
    -0.64
     Bench
    -0.62
     Skydragon
    -0.61
     Plastic
    -0.60
     Waves
    -0.60
    POSITIVE LOGITS
    >)
    1.41
    *)
    1.39
    .).
    1.33
    !).
    1.25
    ?).
    1.25
    ).
    1.24
    !)
    1.22
    ?)
    1.20
    )-
    1.19
    )."
    1.19
    Activations Density 0.117%

    No Known Activations