© 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. 9127
    Prev
    Next
    INDEX
    Explanations

    details or descriptions of specific events or situations

    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
    679
    +0.15
    0.7%
    274
    +0.13
    0.6%
    655
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.15
    0.08
    109
    +0.13
    0.06
    274
    +0.13
    0.06
    Negative Logits
    Ct
    -0.60
     Riding
    -0.59
    Kit
    -0.58
     Station
    -0.57
     Alive
    -0.57
     Alto
    -0.56
    Being
    -0.56
     Everywhere
    -0.55
     Instructor
    -0.54
    ISH
    -0.54
    POSITIVE LOGITS
     resulted
    1.08
     culminated
    1.04
     accompanies
    1.02
     lasted
    1.01
     includes
    1.00
     resembles
    0.97
     resembled
    0.97
     incorporates
    0.96
     amounted
    0.95
     preceded
    0.95
    Activations Density 0.201%

    No Known Activations