© 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. 7551
    Prev
    Next
    INDEX
    Explanations

    references to the name "Weinstein"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the surname "Weinstein."

    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
     chip
    -0.74
    ature
    -0.71
     PK
    -0.68
    atures
    -0.64
     navigation
    -0.63
    KY
    -0.62
     chips
    -0.62
     routes
    -0.62
    cert
    -0.61
     leg
    -0.61
    POSITIVE LOGITS
     Weinstein
    4.15
     Cosby
    1.53
    instein
    1.44
     Weiner
    1.39
     Wein
    1.38
     Harvey
    1.38
     Epstein
    1.34
     Tarant
    1.27
     Canaver
    1.24
     Whedon
    1.21
    Activations Density 0.019%

    No Known Activations