© 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. 11-RES-JB
    11. 22441
    Prev
    Next
    INDEX
    Explanations

    adverbs describing the extent or manner of an action

    oai_token-act-pair · gpt-3.5-turbo

    the word "just" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tie
    -0.67
    lore
    -0.59
     bottleneck
    -0.55
    uberty
    -0.54
     trave
    -0.54
    axis
    -0.53
    ership
    -0.53
     Reprodu
    -0.52
    apolis
    -0.52
    stress
    -0.52
    POSITIVE LOGITS
    ifiable
    1.32
    ifications
    1.27
    IFIED
    0.95
    ifiers
    0.91
    ifying
    0.87
     ONE
    0.87
     about
    0.84
    ices
    0.83
     desserts
    0.82
    IFIC
    0.78
    Activations Density 0.050%

    No Known Activations