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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 1215
    Prev
    Next
    INDEX
    Explanations

    mentions of the company "Monsanto" and related terms like "GMO" and "glyphosate" in a critical context

    oai_token-act-pair · gpt-3.5-turbo

    references to Monsanto and related genetically modified organisms (GMOs)

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

    No Comments

    Negative Logits
    ird
    -0.76
    teen
    -0.73
    aldo
    -0.72
    hani
    -0.70
    pmwiki
    -0.69
    sets
    -0.69
    served
    -0.68
    rine
    -0.67
     Islanders
    -0.66
    ================================================================
    -0.66
    POSITIVE LOGITS
     Monsanto
    0.85
    icide
    0.76
     Roundup
    0.72
    Mobil
    0.72
    icides
    0.68
    weed
    0.68
    osate
    0.67
     glyphosate
    0.67
     Pharma
    0.65
     Corporation
    0.64
    Activations Density 0.011%

    No Known Activations