© 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. 10-RES-JB
    11. 20678
    Prev
    Next
    INDEX
    Explanations

    references to the Associated Press

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Associated Press

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lessly
    -0.68
    gone
    -0.66
    uca
    -0.64
    terday
    -0.64
    upon
    -0.64
    yip
    -0.63
    ettel
    -0.63
    abiding
    -0.62
    gettable
    -0.61
    enegger
    -0.61
    POSITIVE LOGITS
     Press
    1.26
     Journals
    0.98
     Newsp
    0.94
     States
    0.93
     Colleg
    0.86
     Nations
    0.85
    âĢ¦)
    0.81
     Images
    0.79
     PRESS
    0.79
     Correspond
    0.74
    Activations Density 0.015%

    No Known Activations