© 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. 14734
    Prev
    Next
    INDEX
    Explanations

    words related to editing and programming languages

    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
    447
    +0.15
    0.7%
    678
    +0.14
    0.6%
    683
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.15
    0.06
    575
    +0.14
    0.07
    189
    +0.10
    0.05
    Negative Logits
     therap
    -0.73
     charism
    -0.64
    cffffcc
    -0.63
    judicial
    -0.62
    olitics
    -0.60
     condemnation
    -0.60
    PDATE
    -0.59
     peac
    -0.58
    OLOG
    -0.58
    asus
    -0.58
    POSITIVE LOGITS
    paces
    1.23
    pace
    1.21
    hips
    1.20
    hip
    1.18
    mith
    1.07
    ystem
    1.03
     grouped
    1.03
    ource
    1.01
    ources
    1.01
    ongs
    1.00
    Activations Density 0.299%

    No Known Activations