© 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 EvalsExportsAPI 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. 17753
    Prev
    Next
    INDEX
    Explanations

    words related to job roles and responsibilities

    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
    314
    +0.18
    0.8%
    373
    +0.11
    0.5%
    365
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.18
    0.03
    314
    +0.11
    0.01
    463
    +0.09
    0.04
    Negative Logits
     Wilde
    -0.70
     Immunity
    -0.68
     orally
    -0.58
     Unch
    -0.58
    Dialogue
    -0.57
    natureconservancy
    -0.57
     KN
    -0.56
     Kills
    -0.56
     McKenna
    -0.56
     timely
    -0.55
    POSITIVE LOGITS
    tenance
    1.27
    ruction
    1.09
    yright
    1.05
    anced
    0.99
    ousand
    0.98
    quartered
    0.97
    terday
    0.96
    roying
    0.95
    antic
    0.89
    reprene
    0.89
    Activations Density 0.217%

    No Known Activations