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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 22257
    Prev
    Next
    INDEX
    Explanations

    mentions of the company Monsanto and its related products like glyphosate, as well as discussions about GMOs

    oai_token-act-pair · gpt-3.5-turbo

    references to Monsanto and its associated products, particularly glyphosate and GMOs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rom
    -0.78
    ockets
    -0.77
     Blake
    -0.77
     LV
    -0.76
     inn
    -0.76
    irc
    -0.74
     Lumpur
    -0.73
    Stars
    -0.72
    mund
    -0.72
     Logan
    -0.71
    POSITIVE LOGITS
     Monsanto
    3.05
     GMO
    2.99
     pesticide
    2.82
     GMOs
    2.69
     glyphosate
    2.61
     pesticides
    2.49
    osate
    2.36
     Roundup
    2.14
     pestic
    1.84
     Greenpeace
    1.60
    Activations Density 0.038%

    No Known Activations