© 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. 1-RES-JB
    11. 3712
    Prev
    Next
    INDEX
    Explanations

    references to herbicides and herbs

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "herb" or related terms in the context of pesticides and their safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĸ¬
    -0.75
    TER
    -0.74
     Masquerade
    -0.70
     Barcl
    -0.69
    Hart
    -0.68
    TE
    -0.67
     Flyers
    -0.67
     Fas
    -0.67
    NEY
    -0.66
    hani
    -0.66
    POSITIVE LOGITS
     herb
    1.27
    icides
    1.24
    icide
    1.23
    aceous
    1.17
    osate
    1.17
    izabeth
    1.00
     gardens
    0.96
    ophon
    0.93
    ohydrate
    0.92
     weeds
    0.87
    Activations Density 0.005%

    No Known Activations