© 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. 6-RES-JB
    11. 9814
    Prev
    Next
    INDEX
    Explanations

    specialized terms related to different fields such as trade, physical health, military, food, and more

    oai_token-act-pair · gpt-3.5-turbo

    instances of formatting markers or breaks in the text, indicating separate thoughts or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    present
    -0.80
     âĢ¦"
    -0.70
     thereof
    -0.70
     thereto
    -0.69
    ο
    -0.69
    Ïī
    -0.69
    opausal
    -0.68
    .","
    -0.64
     present
    -0.63
    >"
    -0.62
    POSITIVE LOGITS
     Facts
    0.91
     Profile
    0.90
     Analysis
    0.86
     Benefits
    0.85
     Categories
    0.84
     Problems
    0.84
     Differences
    0.84
     Rates
    0.82
     Blocks
    0.81
     Comparison
    0.80
    Activations Density 0.288%

    No Known Activations