© 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. 1-RES-JB
    11. 16381
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptors of different types of cheese

    oai_token-act-pair · gpt-3.5-turbo

    references to cheese

    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
    nant
    -0.90
    NEY
    -0.72
     eminent
    -0.72
    igious
    -0.65
     Citizens
    -0.64
     Latter
    -0.63
     Citizen
    -0.62
     Blueprint
    -0.62
     Walton
    -0.61
     Hep
    -0.61
    POSITIVE LOGITS
     cheese
    1.20
    cloth
    1.15
     Cheese
    1.04
    bowl
    0.94
     chees
    0.93
     popcorn
    0.91
    fruit
    0.91
    weed
    0.90
     sauce
    0.90
     sandwich
    0.90
    Activations Density 0.009%

    No Known Activations