© 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. 1-RES-JB
    11. 3572
    Prev
    Next
    INDEX
    Explanations

    references to businesses or locations with the abbreviation "TD" in them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "TD", likely referencing a specific location or team in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eering
    -0.73
    bidden
    -0.69
    warts
    -0.69
    handle
    -0.67
    ften
    -0.66
    uclear
    -0.66
    д
    -0.66
    iza
    -0.63
     Kinnikuman
    -0.62
    awaru
    -0.62
    POSITIVE LOGITS
     TD
    1.29
    TD
    1.13
    IFF
    0.86
    CHAT
    0.82
    minist
    0.75
     TDs
    0.73
    DS
    0.73
    LC
    0.69
    rians
    0.68
    raq
    0.67
    Activations Density 0.002%

    No Known Activations