© 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. 8-RES-JB
    11. 4301
    Prev
    Next
    INDEX
    Explanations

    names related to Harvey Weinstein

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Harvey" and associated notable figures or events

    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
    */(
    -0.86
    nesota
    -0.74
    scribed
    -0.73
    unal
    -0.70
    76561
    -0.70
    ictionary
    -0.68
    pired
    -0.68
    pires
    -0.67
    uzzle
    -0.67
     lapt
    -0.67
    POSITIVE LOGITS
     Weinstein
    1.33
     Milk
    0.94
     Dent
    0.83
     Nichols
    0.81
     Harvey
    0.76
     Lank
    0.76
     Feldman
    0.75
    ards
    0.74
     Wasserman
    0.74
     Oswald
    0.70
    Activations Density 0.035%

    No Known Activations