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. 10-RES-JB
    6. 12973
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "mushroom"

    oai_token-act-pair · gpt-3.5-turbo

    references to mushrooms and their associations in various contexts, particularly in relation to Indonesia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fare
    -0.95
    ABLE
    -0.75
    book
    -0.70
    ables
    -0.67
     Stras
    -0.64
    able
    -0.62
     Tire
    -0.62
    riages
    -0.61
     Golem
    -0.61
    books
    -0.61
    POSITIVE LOGITS
    ey
    0.79
    ucket
    0.75
    ylum
    0.75
    ea
    0.73
     mushrooms
    0.73
    iat
    0.73
    esi
    0.72
    azar
    0.72
    iversal
    0.71
    izabeth
    0.70
    Activations Density 0.126%

    No Known Activations