© 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. 8-RES-JB
    11. 9580
    Prev
    Next
    INDEX
    Explanations

    historical events and references, specifically related to specific days or groups in history

    oai_token-act-pair · gpt-3.5-turbo

    historical references and discussions about societal evolution

    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
    ebin
    -0.85
    aspx
    -0.78
    Disclaimer
    -0.76
    Shadow
    -0.71
     accuses
    -0.71
    Ingredients
    -0.70
     Oversight
    -0.69
    Question
    -0.68
    rar
    -0.68
     Transparency
    -0.67
    POSITIVE LOGITS
     era
    1.20
     pioneers
    1.16
     Pione
    1.13
     Era
    1.13
     pioneer
    1.11
     eras
    1.06
     contemporaries
    1.02
     proto
    0.97
     WWII
    0.97
     pioneered
    0.95
    Activations Density 1.735%

    No Known Activations