© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 15967
    Prev
    Next
    INDEX
    Explanations

    phrases related to chemical additives and substances with potential health implications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of chemical additives and their potential harmful effects

    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
    ership
    -0.85
    thumbnails
    -0.76
    ļé
    -0.70
    irc
    -0.70
    Chair
    -0.68
    cffffcc
    -0.67
     gaping
    -0.66
    Bird
    -0.66
    awar
    -0.64
    ĺħ
    -0.63
    POSITIVE LOGITS
     additives
    1.13
     salts
    1.09
     oxid
    1.05
     chemically
    1.04
     ions
    1.03
     molecules
    0.99
     ingested
    0.98
     metabolites
    0.98
     substances
    0.97
     residues
    0.97
    Activations Density 0.174%

    No Known Activations