© 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. 5347
    Prev
    Next
    INDEX
    Explanations

    mentions of the specific name "Waters"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the filmmaker John Waters

    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
    âĹ¼
    -0.84
    PsyNetMessage
    -0.74
    ient
    -0.74
     Canucks
    -0.68
     ger
    -0.67
    arin
    -0.67
    Jun
    -0.64
     imperfect
    -0.63
    UG
    -0.63
    NET
    -0.63
    POSITIVE LOGITS
     Waters
    2.61
     Stevenson
    1.50
     slaughter
    1.37
    waters
    1.36
     Owens
    1.27
     Wick
    1.24
     Slaughter
    1.24
     Wool
    1.10
     Meat
    1.05
     Heller
    1.04
    Activations Density 0.039%

    No Known Activations