© 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. 23750
    Prev
    Next
    INDEX
    Explanations

    references to people named "Gordon"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Gordon" in various contexts

    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
    ylum
    -0.84
    ItemTracker
    -0.83
    inyl
    -0.80
    ledged
    -0.77
    ngth
    -0.77
     Archdemon
    -0.77
    edIn
    -0.75
    urities
    -0.73
    hma
    -0.73
    Rated
    -0.73
    POSITIVE LOGITS
     Ramsay
    1.31
     Yards
    0.89
     Wass
    0.88
     Hayward
    0.87
     Kling
    0.80
     Freeman
    0.76
    buster
    0.76
     Ramsey
    0.76
     Bombay
    0.72
    Gordon
    0.70
    Activations Density 0.027%

    No Known Activations