© 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. 8-RES-JB
    11. 19302
    Prev
    Next
    INDEX
    Explanations

    references to specific names or terms related to agriculture and herbicides

    oai_token-act-pair · gpt-3.5-turbo

    mentions of herbicides and related substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Charter
    -0.72
    etting
    -0.71
     Mongo
    -0.68
     Dunk
    -0.65
    ultz
    -0.62
    cing
    -0.61
     Telegram
    -0.60
     Hebdo
    -0.60
     postage
    -0.60
    ":-
    -0.59
    POSITIVE LOGITS
    aceous
    1.38
    icide
    1.31
    icides
    1.28
    icals
    1.07
    istry
    0.99
    icidal
    0.99
    ohydrate
    0.95
    iv
    0.95
    ivated
    0.95
    osate
    0.94
    Activations Density 0.032%

    No Known Activations