© 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. 8-RES-JB
    11. 22427
    Prev
    Next
    INDEX
    Explanations

    technology-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to programs, services, and systems related to technology or online platforms

    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
     Flavoring
    -0.73
     evils
    -0.64
     Buildings
    -0.64
     Sect
    -0.64
    inas
    -0.64
     Scenes
    -0.62
     Hits
    -0.62
    inventoryQuantity
    -0.61
     perish
    -0.61
     Conclusion
    -0.60
    POSITIVE LOGITS
     dedicated
    1.05
     whereby
    1.03
     called
    0.91
    mable
    0.90
     modeled
    0.84
     specializing
    0.81
     allowing
    0.79
     devoted
    0.78
    matic
    0.78
     documenting
    0.78
    Activations Density 0.448%

    No Known Activations