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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8969
    Prev
    Next
    INDEX
    Explanations

    instances of software bugs being fixed

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "bug" related to software issues or errors

    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
    achy
    -0.74
    ophers
    -0.74
    zers
    -0.73
    kus
    -0.68
    ederation
    -0.68
    estyles
    -0.68
    ells
    -0.66
     CHO
    -0.65
    uania
    -0.64
    zees
    -0.64
    POSITIVE LOGITS
    Bug
    1.03
    bug
    1.01
    bugs
    0.95
     bug
    0.94
    fix
    0.87
     Bug
    0.86
    fixes
    0.84
     bugs
    0.83
    bear
    0.82
     bounty
    0.81
    Activations Density 0.006%

    No Known Activations