Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 21671
    Prev
    Next
    INDEX
    Explanations

    mentions of insects or software issues that need to be fixed

    oai_token-act-pair · gpt-3.5-turbo

    references to bugs in various contexts, particularly in software or game development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itone
    -0.77
    cend
    -0.66
    CHR
    -0.65
     Christian
    -0.65
     proclamation
    -0.65
     Chr
    -0.64
    itness
    -0.64
    scription
    -0.64
    istry
    -0.63
     outlet
    -0.63
    POSITIVE LOGITS
     bugs
    3.80
    bugs
    2.73
     Bugs
    2.45
     bug
    1.96
    bug
    1.83
     glitches
    1.79
     insects
    1.77
     vulnerabilities
    1.72
     beetles
    1.61
     pests
    1.59
    Activations Density 0.013%

    No Known Activations