© 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. 0-RES-JB
    11. 8364
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of 'weeding out'

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "weed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lib
    -0.86
     Lib
    -0.78
    akis
    -0.73
     Titanic
    -0.69
    Card
    -0.69
     Rail
    -0.68
     Kag
    -0.68
    Ãł
    -0.68
    nas
    -0.67
    BBC
    -0.67
    POSITIVE LOGITS
     weed
    3.96
     Weed
    2.38
     weeds
    2.13
    weed
    2.05
     cannabis
    1.63
     marijuana
    1.63
    arijuana
    1.61
     Marijuana
    1.58
     herb
    1.56
     dope
    1.52
    Activations Density 0.014%

    No Known Activations