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. 0-RES-JB
    6. 3389
    Prev
    Next
    INDEX
    Explanations

    words related to travel documents, particularly passports

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to passports and nationality

    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
    lees
    -0.77
     Orn
    -0.69
    aste
    -0.67
     Ner
    -0.66
    lee
    -0.66
     Darrell
    -0.66
    licts
    -0.65
    Wood
    -0.65
    Feed
    -0.63
    nut
    -0.63
    POSITIVE LOGITS
     passport
    3.67
     passports
    3.30
     visa
    1.90
     visas
    1.52
     nationality
    1.51
     citizenship
    1.47
     luggage
    1.42
     suitcase
    1.36
     Visa
    1.31
     consulate
    1.23
    Activations Density 0.010%

    No Known Activations