© 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. 9-RES-JB
    11. 15478
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically those relating to various names and titles

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals and organizations in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONSORED
    -0.53
    IBLE
    -0.47
    ãĤ¢ãĥ«
    -0.45
    depending
    -0.43
     Canaver
    -0.41
     ¯
    -0.40
     WRITE
    -0.40
    abus
    -0.40
    FontSize
    -0.39
    ?????-
    -0.39
    POSITIVE LOGITS
     and
    1.08
     etc
    0.95
     or
    0.93
    ®,
    0.77
     &
    0.75
     AND
    0.70
     versus
    0.68
    -,
    0.68
     et
    0.66
    ,
    0.66
    Activations Density 2.262%

    No Known Activations