© 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. 6-RES-JB
    11. 12045
    Prev
    Next
    INDEX
    Explanations

    medical terms and conditions, including psychiatric and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    references to political and social issues

    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
     scout
    -0.78
    theless
    -0.73
     interchange
    -0.68
    finder
    -0.66
    bnb
    -0.63
     sorcerer
    -0.63
     err
    -0.63
     english
    -0.62
     abroad
    -0.62
    shapeshifter
    -0.61
    POSITIVE LOGITS
    aches
    0.95
    ared
    0.94
    cknowled
    0.92
    overed
    0.90
    secut
    0.89
    emic
    0.87
    rupted
    0.87
    aped
    0.87
    alties
    0.86
    ots
    0.86
    Activations Density 0.310%

    No Known Activations