© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 19764
    Prev
    Next
    INDEX
    Explanations

    words related to a specific location or event named "Sur"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Sur," suggesting it identifies mentions of a location or entity associated with "Sur."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naires
    -0.83
    hetti
    -0.75
    heid
    -0.73
    Constructed
    -0.69
    itsch
    -0.65
     LIA
    -0.65
    OGR
    -0.64
    YC
    -0.63
     Archdemon
    -0.62
     Goddard
    -0.61
    POSITIVE LOGITS
    geon
    1.21
    geons
    1.12
    rounded
    1.01
    fer
    0.96
    render
    0.96
    fing
    0.93
    ports
    0.92
    ples
    0.88
    round
    0.88
    prising
    0.85
    Activations Density 0.003%

    No Known Activations