© 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 EvalsExportsinterp-engineNEWAPI 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. 22271
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "dis-"

    oai_token-act-pair · gpt-4o-miniTriggered 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
    19
    +0.13
    0.6%
    0
    +0.11
    0.5%
    167
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    19
    +0.13
    0.02
    658
    +0.11
    0.02
    0
    +0.10
    0.02
    Negative Logits
    hetti
    -0.69
    glers
    -0.65
     Hanna
    -0.64
     Osw
    -0.64
    OPLE
    -0.64
     Kinnikuman
    -0.64
     Juliet
    -0.63
     Scotia
    -0.62
     Lans
    -0.62
     Burr
    -0.61
    POSITIVE LOGITS
    cipl
    1.21
    claimer
    1.19
    ruption
    1.17
    comfort
    1.14
    enfranch
    1.14
    qus
    1.13
    cerning
    1.11
    burse
    1.11
    placed
    1.10
    puted
    1.10
    Activations Density 0.011%

    No Known Activations