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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 22582
    Prev
    Next
    INDEX
    Explanations

    ingredients and instructions in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    cooking instructions and related measurement details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subscribing
    -0.75
    ¥µ
    -0.75
     headlined
    -0.73
     Gund
    -0.72
    href
    -0.71
     Samar
    -0.66
     interoper
    -0.65
     cryptic
    -0.64
     fleets
    -0.64
     Ghosts
    -0.64
    POSITIVE LOGITS
    Ingredients
    1.14
     Ingredients
    1.02
     mixture
    1.02
     ingredients
    1.00
    poons
    0.95
     freezer
    0.94
     ingred
    0.93
    ulsion
    0.91
    redients
    0.90
     skillet
    0.90
    Activations Density 0.624%

    No Known Activations