© 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. 10-RES-JB
    11. 2957
    Prev
    Next
    INDEX
    Explanations

    instructions or steps in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to baking and cooking processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nanto
    -0.81
     adrenaline
    -0.79
    href
    -0.79
     Adren
    -0.76
     Samar
    -0.71
    æ©Ł
    -0.70
     Telecom
    -0.69
    aughs
    -0.66
     acron
    -0.66
    ocrin
    -0.66
    POSITIVE LOGITS
     parchment
    1.37
     pastry
    1.16
     freezer
    1.16
     baking
    1.15
     skillet
    1.13
     tray
    1.10
    archment
    1.02
     lined
    1.02
     dish
    1.00
     dough
    0.99
    Activations Density 0.181%

    No Known Activations