© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3935
    Prev
    Next
    INDEX
    Explanations

    information related to news articles, authors, publications, and content sources

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    key information about individuals and their backgrounds in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    Âł
    -0.13
     favour
    -0.12
     [...]
    -0.11
     harbour
    -0.11
     breed
    -0.11
     mate
    -0.11
     Âł
    -0.10
     [âĢ¦]
    -0.10
     kindly
    -0.10
     rapes
    -0.10
    POSITIVE LOGITS
    ThumbnailImage
    0.14
    KC
    0.14
    Methods
    0.13
     practition
    0.13
    EXT
    0.13
    VIS
    0.13
    TPPStreamerBot
    0.13
    Stew
    0.13
    Ext
    0.13
    Ą
    0.13
    Activations Density 25.037%

    No Known Activations