© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 6812
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns related to Malaysia and Indonesia

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical locations and political contexts

    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
    Wisconsin
    -1.14
    Michigan
    -1.08
     Vermont
    -1.07
     Steelers
    -1.04
     Erie
    -1.02
    Ohio
    -0.99
     Fallon
    -0.98
     Pittsburgh
    -0.97
    Sanders
    -0.95
     Niagara
    -0.94
    POSITIVE LOGITS
     Jakarta
    2.42
     Indonesian
    2.38
     Indones
    2.36
     Indonesia
    2.30
     Malays
    2.17
     Kuala
    2.01
     Malaysian
    1.95
     Malaysia
    1.94
     Singapore
    1.72
     Brune
    1.55
    Activations Density 0.325%

    No Known Activations