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. 3-RES-JB
    6. 7838
    Prev
    Next
    INDEX
    Explanations

    information about recipes and cooking

    oai_token-act-pair · gpt-3.5-turbo

    references to recipes and cooking-related content

    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
     Hezbollah
    -0.62
     disputed
    -0.62
     discredited
    -0.62
    xit
    -0.61
     Islamist
    -0.61
     Kissinger
    -0.60
     terrorism
    -0.60
     Osama
    -0.59
     Exxon
    -0.58
     expelled
    -0.58
    POSITIVE LOGITS
     crochet
    0.77
     lovely
    0.75
     :)
    0.72
     ðŁĻĤ
    0.70
     delicious
    0.70
     Vegan
    0.70
     cheesy
    0.68
     ingred
    0.67
     wonderful
    0.67
     HUGE
    0.66
    Activations Density 2.503%

    No Known Activations