Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 11632
    Prev
    Next
    INDEX
    Explanations

    names or words ending in "owitz"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals and concepts related to antisemitism

    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
    itarian
    -0.83
    ities
    -0.73
    idable
    -0.73
    ainers
    -0.71
     NCT
    -0.69
    istically
    -0.67
    ingham
    -0.66
     Seller
    -0.66
    ipper
    -0.64
    changed
    -0.64
    POSITIVE LOGITS
    quit
    0.72
    cz
    0.70
    eln
    0.70
    cn
    0.69
    chnology
    0.68
     respons
    0.64
    terness
    0.63
    nec
    0.62
    henko
    0.61
    rils
    0.60
    Activations Density 0.026%

    No Known Activations