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. 6-RES-JB
    6. 9085
    Prev
    Next
    INDEX
    Explanations

    names or agencies related to immigration and customs enforcement

    oai_token-act-pair · gpt-3.5-turbo

    mentions of immigration and customs enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tsky
    -0.80
    dfx
    -0.80
    keyes
    -0.73
    oshenko
    -0.72
    cipled
    -0.72
     Zup
    -0.71
    oller
    -0.71
    kered
    -0.67
    pling
    -0.66
    igmatic
    -0.65
    POSITIVE LOGITS
     commodities
    0.66
     subsistence
    0.65
     Affordable
    0.65
     Simulator
    0.64
    sector
    0.63
    phia
    0.63
     Rehab
    0.63
    ourses
    0.63
     Spur
    0.63
     Regulatory
    0.62
    Activations Density 0.577%

    No Known Activations