© 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. 11-RES-JB
    11. 1022
    Prev
    Next
    INDEX
    Explanations

    quotes from various people in a formal context

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their roles or positions in official contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mascot
    -0.83
     destiny
    -0.68
    animate
    -0.67
    tumblr
    -0.67
     Shutterstock
    -0.65
    DragonMagazine
    -0.65
     Dwarf
    -0.63
     Messiah
    -0.63
     litter
    -0.62
    osterone
    -0.62
    POSITIVE LOGITS
     briefed
    1.46
     familiar
    1.29
     priv
    1.04
     knowledgeable
    1.02
    amiliar
    0.99
     speaking
    0.97
     reviewed
    0.95
     interviewed
    0.90
     intimately
    0.89
     consulted
    0.89
    Activations Density 0.137%

    No Known Activations