© 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. 1038
    Prev
    Next
    INDEX
    Explanations

    law firms and legal partnerships

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and ampersands indicating connections or relationships

    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
    pmwiki
    -0.87
    SPONSORED
    -0.85
    aned
    -0.77
    terday
    -0.77
    emort
    -0.77
    abyte
    -0.75
    uggest
    -0.73
    Picture
    -0.72
    nown
    -0.71
    imum
    -0.70
    POSITIVE LOGITS
     Associates
    1.60
     Sons
    1.40
     Company
    1.31
     Partners
    1.21
     Co
    1.16
     Sullivan
    1.09
     Sutherland
    1.08
     Dunn
    1.04
     McKenzie
    1.02
     Son
    1.02
    Activations Density 0.061%

    No Known Activations