Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 63
    Prev
    Next
    INDEX
    Explanations

    words related to pepper in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to pepper and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NG
    -0.79
    ications
    -0.76
     Genie
    -0.74
     Generations
    -0.72
     Morg
    -0.71
    sonian
    -0.69
    rift
    -0.68
    Kenn
    -0.68
    TT
    -0.67
     Ik
    -0.66
    POSITIVE LOGITS
     pepper
    3.80
     peppers
    2.83
     Pepper
    2.20
     chili
    1.40
     bean
    1.30
     spices
    1.27
     spice
    1.27
     garlic
    1.22
     spicy
    1.19
     tomato
    1.17
    Activations Density 0.016%

    No Known Activations