© 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. 11349
    Prev
    Next
    INDEX
    Explanations

    company names and specific details about their locations, products, and activities

    oai_token-act-pair · gpt-3.5-turbo

    references to websites or online entities

    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
     increments
    -0.66
    sed
    -0.63
     retri
    -0.62
     mater
    -0.61
    orgetown
    -0.60
     haun
    -0.58
    isms
    -0.58
     Sieg
    -0.57
    eteen
    -0.57
     overhe
    -0.56
    POSITIVE LOGITS
     themselves
    1.37
     Their
    1.03
    Their
    1.03
    their
    0.97
    senal
    0.91
     THEIR
    0.90
     their
    0.85
    selves
    0.85
     sponsoring
    0.73
     logo
    0.73
    Activations Density 0.641%

    No Known Activations