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. 11-RES-JB
    6. 19537
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographical locations and political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to Cambodian news and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Milwaukee
    -1.06
    Wisconsin
    -1.00
    Scotland
    -0.96
    Madison
    -0.88
     Braun
    -0.87
     Bowie
    -0.84
     Wisconsin
    -0.84
    ERN
    -0.84
    Walker
    -0.83
     Rutherford
    -0.82
    POSITIVE LOGITS
     Thai
    2.40
     Bangkok
    2.34
     Thailand
    2.24
     Cambod
    2.10
     Cambodia
    1.96
     Nguyen
    1.90
     Laos
    1.89
     Vietnamese
    1.83
     Chao
    1.68
     Ying
    1.65
    Activations Density 0.332%

    No Known Activations