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. 9-RES-JB
    6. 12720
    Prev
    Next
    INDEX
    Explanations

    mentions of international locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Navajo
    -1.08
     salsa
    -1.04
    zona
    -0.93
     Albuquerque
    -0.93
     Guatem
    -0.93
     Romo
    -0.93
     Guerrero
    -0.92
     tacos
    -0.92
     taco
    -0.92
     Morales
    -0.91
    POSITIVE LOGITS
    England
    1.73
     England
    1.66
     London
    1.57
    Scotland
    1.54
    London
    1.53
     Yorkshire
    1.50
     Britain
    1.48
     Scotland
    1.47
     Westminster
    1.47
     Edinburgh
    1.47
    Activations Density 0.754%

    No Known Activations