© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9856
    Prev
    Next
    INDEX
    Explanations

    names and surnames containing the specific character sequence "ison"

    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
    515
    +0.12
    0.5%
    124
    +0.10
    0.5%
    276
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.02
    353
    +0.10
    0.01
    326
    +0.10
    0.02
    Negative Logits
    undo
    -0.83
    astical
    -0.79
    astically
    -0.77
    estones
    -0.77
    appers
    -0.74
    ulative
    -0.71
    rimination
    -0.71
    ifts
    -0.70
    IFT
    -0.67
    locked
    -0.67
    POSITIVE LOGITS
    nette
    1.04
    naire
    1.02
    ette
    0.96
    ous
    0.90
    ary
    0.88
    eers
    0.88
    nect
    0.87
    eering
    0.85
    neau
    0.85
     Wonderland
    0.83
    Activations Density 0.049%

    No Known Activations