© 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. 8-RES-JB
    11. 20413
    Prev
    Next
    INDEX
    Explanations

    technical terms related to fixing bugs in software development

    oai_token-act-pair · gpt-3.5-turbo

    references to bugs and errors in software, particularly in gaming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.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

    Negative Logits
    —-
    -0.81
    SPONSORED
    -0.72
    Education
    -0.72
    "—
    -0.69
    Äĵ
    -0.69
     ÂŃ
    -0.68
    education
    -0.67
    tainment
    -0.67
     Kinnikuman
    -0.67
    Advertisement
    -0.67
    POSITIVE LOGITS
     tooltip
    1.10
     incorrectly
    1.06
     respawn
    1.00
     overwrite
    1.00
     GUI
    0.92
     errone
    0.90
     popup
    0.88
     incorrect
    0.87
     improperly
    0.85
     UI
    0.83
    Activations Density 0.420%

    No Known Activations