© 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. 7-RES-JB
    11. 12696
    Prev
    Next
    INDEX
    Explanations

    words related to sports matches

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "match"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.75
    achev
    -0.74
    irtual
    -0.67
    raft
    -0.65
    ible
    -0.64
    wcs
    -0.63
    arger
    -0.62
    ngth
    -0.62
    Asset
    -0.61
    bold
    -0.61
    POSITIVE LOGITS
    making
    0.97
    maker
    0.95
    nings
    0.88
    makers
    0.88
    sticks
    0.80
    match
    0.79
    stick
    0.78
    eering
    0.78
    eer
    0.77
    eers
    0.75
    Activations Density 0.024%

    No Known Activations