© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5393
    Prev
    Next
    INDEX
    Explanations

    phrases related to coding or programming instructions

    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
    159
    +0.16
    0.7%
    393
    +0.11
    0.5%
    408
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.16
    0.08
    95
    +0.11
    0.05
    589
    +0.11
    0.05
    Negative Logits
    icons
    -0.96
    tones
    -0.80
    acers
    -0.79
    aughtered
    -0.79
    anches
    -0.78
    aws
    -0.78
    bats
    -0.74
    gress
    -0.74
    aques
    -0.73
    utical
    -0.73
    POSITIVE LOGITS
     phenomenon
    1.23
     trope
    1.13
     particular
    1.13
     newfound
    1.11
     discrepancy
    1.04
     latter
    1.03
     aspect
    1.02
     predicament
    0.97
     type
    0.96
     kind
    0.96
    Activations Density 0.151%

    No Known Activations