© 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. 1-RES-JB
    11. 22056
    Prev
    Next
    INDEX
    Explanations

    keywords related to software bug tracking and fixing

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Bug" or variations related to software issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FORMATION
    -0.72
    535
    -0.72
    ×Ķ
    -0.68
    istors
    -0.67
     learning
    -0.65
    CHR
    -0.64
     oxy
    -0.64
    ONT
    -0.64
    650
    -0.62
    801
    -0.62
    POSITIVE LOGITS
    Bug
    1.23
     Bug
    1.15
     Bugs
    1.01
    gers
    0.96
    enhagen
    0.91
    ging
    0.89
    zilla
    0.88
    bug
    0.88
    ger
    0.88
    reau
    0.86
    Activations Density 0.011%

    No Known Activations