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. 1098
    Prev
    Next
    INDEX
    Explanations

    mentions of different countries and governments

    oai_token-act-pair · gpt-3.5-turbo

    references to specific national governments or origin countries

    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
    outine
    -0.63
    xual
    -0.63
    ãĥ´ãĤ¡
    -0.60
     Chatt
    -0.60
     Vert
    -0.60
     Title
    -0.59
     VID
    -0.59
     Ruin
    -0.59
     Shall
    -0.58
     Tsu
    -0.57
    POSITIVE LOGITS
    AAF
    0.80
     Embassy
    0.78
    ports
    0.78
     embassy
    0.75
     Quadro
    0.73
     diplomats
    0.71
    assies
    0.70
    sonian
    0.70
     consulate
    0.67
    ITED
    0.67
    Activations Density 0.395%

    No Known Activations