© 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. 24262
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "pre-."

    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
    0
    +0.12
    0.5%
    541
    +0.10
    0.4%
    566
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    +0.12
    0.04
    541
    +0.10
    0.03
    433
    +0.10
    0.03
    Negative Logits
    loo
    -0.73
     Shack
    -0.67
     Ago
    -0.66
    IBLE
    -0.66
     Heights
    -0.65
    Ø©
    -0.63
     Hearts
    -0.63
     Cup
    -0.63
     GOODMAN
    -0.62
     Slug
    -0.62
    POSITIVE LOGITS
    requisites
    1.34
    occup
    1.31
    ceed
    1.22
    fecture
    1.19
    req
    1.18
    lude
    1.15
    occupied
    1.14
    achers
    1.13
    hens
    1.11
    empt
    1.11
    Activations Density 0.018%

    No Known Activations