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

    Neuronpedia

    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. 2-RES-JB
    11. 7808
    Prev
    Next
    INDEX
    Explanations

    keywords related to software bugs

    oai_token-act-pair · gpt-3.5-turbo

    references to "bugs" in various contexts, particularly in software or programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CHR
    -0.71
    ETH
    -0.69
    ONT
    -0.68
    ×Ķ
    -0.67
    ×Ļ×
    -0.66
    ×ķ
    -0.64
    535
    -0.64
     POLIT
    -0.63
     chloride
    -0.62
    ISO
    -0.61
    POSITIVE LOGITS
    Bug
    1.10
    gers
    1.06
     Bug
    1.05
    ging
    0.99
    ger
    0.97
    enhagen
    0.96
    zilla
    0.94
    gered
    0.93
    ged
    0.91
     Bugs
    0.90
    Activations Density 0.007%

    No Known Activations