© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 22107
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development, particularly those related to identifying and resolving issues in software (bugs)

    oai_token-act-pair · gpt-3.5-turbo

    references to "bug" and related terms associated with software issues and fixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sclerosis
    -0.74
     Mechdragon
    -0.71
     Trinidad
    -0.68
     glaciers
    -0.67
     bargaining
    -0.63
     Juda
    -0.63
     tallest
    -0.62
     towers
    -0.61
     Hemp
    -0.61
     ministry
    -0.61
    POSITIVE LOGITS
    fixes
    1.34
    fix
    1.30
    zilla
    1.20
    bear
    1.13
    gered
    1.03
     bounty
    1.02
    bug
    0.98
    fixed
    0.96
    atti
    0.93
     fixes
    0.92
    Activations Density 0.029%

    No Known Activations