© 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. 10-RES-JB
    11. 11579
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to the direction "North."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "North" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rative
    -0.70
    ration
    -0.70
    xxxxxxxx
    -0.64
     confir
    -0.63
    TED
    -0.60
    TING
    -0.60
    eer
    -0.59
     tee
    -0.59
    ILA
    -0.58
    ually
    -0.58
    POSITIVE LOGITS
    ampton
    1.43
     Carolina
    1.20
    western
    1.11
     Dakota
    1.10
    umber
    1.05
     Korea
    1.05
     Pole
    1.04
    west
    1.03
    ridge
    1.03
    woods
    1.00
    Activations Density 0.034%

    No Known Activations