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. 11-RES-JB
    6. 17881
    Prev
    Next
    INDEX
    Explanations

    information related to food labels and potentially harmful substances mentioned on them

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to food labeling and consumer safety concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lenin
    -0.75
    qqa
    -0.70
    Completed
    -0.68
    oenix
    -0.68
     Reid
    -0.67
     tor
    -0.67
     tempo
    -0.66
     chess
    -0.64
    anu
    -0.64
    aez
    -0.63
    POSITIVE LOGITS
     FDA
    1.57
     allerg
    1.53
     ingredient
    1.49
     additives
    1.49
     labeling
    1.48
     packaging
    1.43
     ingredients
    1.43
    Ingredients
    1.36
     gluten
    1.36
     dietary
    1.34
    Activations Density 0.647%

    No Known Activations