© 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. 12359
    Prev
    Next
    INDEX
    Explanations

    first-person singular pronouns followed by verbs expressing thoughts or emotions

    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
    477
    +0.11
    0.5%
    185
    +0.09
    0.4%
    102
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.11
    0.05
    718
    +0.09
    0.06
    762
    +0.09
    0.07
    Negative Logits
     meanwhile
    -0.69
     Lank
    -0.64
     Lys
    -0.60
     Hanson
    -0.59
     Locations
    -0.58
     Lanka
    -0.58
     Tracks
    -0.58
     Kamp
    -0.56
    eret
    -0.56
    ;;;;;;;;
    -0.56
    POSITIVE LOGITS
    Reviewer
    0.95
     suddenly
    0.88
     inexpl
    0.84
    apsed
    0.81
     unexpectedly
    0.80
    uddenly
    0.80
     mysteriously
    0.78
    Suddenly
    0.75
    iphany
    0.72
    amorph
    0.72
    Activations Density 0.773%

    No Known Activations