© 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. 7-RES-JB
    11. 17763
    Prev
    Next
    INDEX
    Explanations

    words related to herbs and herbicides, particularly focusing on the herbicide glyphosate

    oai_token-act-pair · gpt-3.5-turbo

    terms related to herbicides and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mongo
    -0.75
     Charter
    -0.68
     Mast
    -0.67
     Glock
    -0.64
     Telegram
    -0.63
     Agenda
    -0.63
     Adidas
    -0.62
     Wolves
    -0.62
     Pace
    -0.61
    --------
    -0.61
    POSITIVE LOGITS
    aceous
    1.33
    icides
    1.19
    icide
    1.19
    icum
    1.16
    osate
    1.07
    istry
    1.06
    icals
    1.02
    ohydrate
    0.99
    icans
    0.95
    itage
    0.95
    Activations Density 0.036%

    No Known Activations