© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15402
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development and tools

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    679
    +0.15
    0.7%
    420
    +0.13
    0.6%
    289
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.15
    0.02
    679
    +0.13
    0.03
    289
    +0.12
    0.01
    Negative Logits
     Sons
    -0.90
     sons
    -0.66
    ipop
    -0.63
     Qiao
    -0.63
    otos
    -0.62
     mosqu
    -0.62
    ilipp
    -0.60
     outgoing
    -0.59
    ãģ®å®
    -0.59
     decad
    -0.59
    POSITIVE LOGITS
    kit
    1.54
    tips
    1.46
    tip
    1.11
    sonian
    1.10
    belt
    1.05
    chain
    1.04
     tools
    0.99
    set
    0.98
    chains
    0.95
    assisted
    0.93
    Activations Density 0.032%

    No Known Activations