© 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. 3-RES-JB
    11. 652
    Prev
    Next
    INDEX
    Explanations

    references related to the herbicide "weed killer" and mentions of the word "weed" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to "weed" and its related contexts or meanings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ultz
    -0.72
    cffffcc
    -0.68
    */(
    -0.67
    uras
    -0.65
    ctic
    -0.62
    jri
    -0.60
    CBC
    -0.59
    hani
    -0.59
     Theresa
    -0.59
    erald
    -0.59
    POSITIVE LOGITS
     weed
    1.02
    killer
    0.93
    atio
    0.89
     Weed
    0.87
    killers
    0.81
    ipop
    0.80
    bowl
    0.76
     buds
    0.74
    weed
    0.72
    apons
    0.71
    Activations Density 0.009%

    No Known Activations