© 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. 1-RES-JB
    11. 14507
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking instructions for recipes

    oai_token-act-pair · gpt-3.5-turbo

    ingredients and measurements in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Geh
    -0.80
     defending
    -0.80
     EM
    -0.75
     Grayson
    -0.75
     ACL
    -0.74
     Standing
    -0.73
     charging
    -0.71
     overseeing
    -0.71
     patrolling
    -0.70
     EEG
    -0.70
    POSITIVE LOGITS
    Ingredients
    1.23
     tasted
    1.12
     nutrit
    1.10
     soup
    1.10
     salad
    1.08
     cereal
    1.08
     flav
    1.08
     servings
    1.07
     broth
    1.07
     toast
    1.06
    Activations Density 0.635%

    No Known Activations