© 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. 11-RES-JB
    11. 15757
    Prev
    Next
    INDEX
    Explanations

    instructions or suggestions related to food preparation

    oai_token-act-pair · gpt-3.5-turbo

    recommendations for easy-to-make recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    emis
    -0.79
     Surveillance
    -0.69
     Cantor
    -0.69
     correspondence
    -0.68
     Cable
    -0.68
    Fax
    -0.66
    Voice
    -0.65
    ELD
    -0.63
     Aerospace
    -0.63
     Bridges
    -0.63
    POSITIVE LOGITS
     eat
    1.51
     ate
    1.34
     tasted
    1.33
     eaten
    1.32
     taste
    1.30
     overc
    1.27
     cook
    1.27
     bake
    1.25
     roast
    1.24
     microw
    1.24
    Activations Density 0.260%

    No Known Activations