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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 22059
    Prev
    Next
    INDEX
    Explanations

    mentions of or descriptions related to frogs

    oai_token-act-pair · gpt-3.5-turbo

    references to frogs and amphibians

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Commonwealth
    -0.72
    HC
    -0.70
     Hemp
    -0.68
     Chamberlain
    -0.67
    Definition
    -0.64
     Goods
    -0.64
    QUIRE
    -0.62
    Interstitial
    -0.59
     Defin
    -0.57
     Occupations
    -0.57
    POSITIVE LOGITS
    lings
    1.09
     frogs
    1.07
    grass
    1.07
    fish
    1.01
    weed
    1.00
    mons
    0.96
    tailed
    0.95
     frog
    0.90
    frog
    0.87
    flies
    0.85
    Activations Density 0.007%

    No Known Activations