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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11958
    Prev
    Next
    INDEX
    Explanations

    information about harmful chemicals in food and the environment

    oai_token-act-pair · gpt-3.5-turbo

    references to toxic chemicals and their associated health risks

    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
    issance
    -0.76
     Twins
    -0.72
    iku
    -0.72
     unification
    -0.71
    lia
    -0.69
     reception
    -0.69
     Wings
    -0.67
     Jub
    -0.67
     orderly
    -0.66
    natureconservancy
    -0.66
    POSITIVE LOGITS
     contaminants
    1.45
     toxins
    1.44
     chemicals
    1.44
     pesticides
    1.40
     pollutants
    1.37
     additives
    1.37
     contamin
    1.33
     substances
    1.32
    aldehyde
    1.30
     metabolites
    1.21
    Activations Density 0.296%

    No Known Activations