© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23946
    Prev
    Next
    INDEX
    Explanations

    instances of the word "complete" and its variations, indicating fulfillment or finishing tasks

    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
    59
    +0.12
    0.5%
    665
    +0.11
    0.5%
    207
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.12
    0.03
    59
    +0.11
    0.02
    207
    +0.11
    0.02
    Negative Logits
    pter
    -0.71
    maid
    -0.69
    lua
    -0.69
    inn
    -0.67
    people
    -0.65
    gypt
    -0.65
    spr
    -0.62
    tal
    -0.62
    worn
    -0.62
    Bey
    -0.62
    POSITIVE LOGITS
    TAIN
    0.86
     feasibility
    0.84
     tasks
    0.82
    issance
    0.81
     renovations
    0.80
     preparations
    0.75
     paperwork
    0.74
    CLASSIFIED
    0.73
    İĭ
    0.72
    é¾
    0.70
    Activations Density 0.034%

    No Known Activations