© 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. 2975
    Prev
    Next
    INDEX
    Explanations

    technology-related terms or concepts, particularly related to software and fiction

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

    symbols or characters that are often used in creative or artistic contexts

    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
     Mous
    -0.62
     Crom
    -0.57
     Moss
    -0.56
    chell
    -0.56
     Nam
    -0.55
     Sum
    -0.53
     Sprint
    -0.52
     Mall
    -0.52
     wom
    -0.52
     Saur
    -0.52
    POSITIVE LOGITS
    ľ
    1.77
    ¬
    1.34
    ®
    1.30
    Ń
    1.29
    ¼
    1.29
    Ł
    1.25
    ¡
    1.25
    Ķ
    1.24
    ł
    1.22
    ½
    1.21
    Activations Density 0.435%

    No Known Activations