© 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. 22138
    Prev
    Next
    INDEX
    Explanations

    email addresses and references to email communication

    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
    214
    +0.12
    0.6%
    598
    +0.11
    0.5%
    315
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.01
    598
    +0.11
    0.02
    214
    +0.11
    0.03
    Negative Logits
     temples
    -0.74
     Expand
    -0.68
     Inher
    -0.67
     signage
    -0.66
     Judges
    -0.64
     Lunar
    -0.63
     Wander
    -0.63
     Survive
    -0.63
     Mud
    -0.62
     Crafting
    -0.61
    POSITIVE LOGITS
    olicited
    1.02
    onse
    0.93
     Abedin
    0.86
    Sent
    0.85
    Message
    0.82
    reply
    0.81
    Subject
    0.78
     <[
    0.77
     Podesta
    0.76
     john
    0.76
    Activations Density 0.141%

    No Known Activations