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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5038
    Prev
    Next
    INDEX
    Explanations

    references to the United States of America and related terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to the United States and its characteristics

    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
     councillor
    -0.98
     councillors
    -0.92
     licence
    -0.87
     Bok
    -0.82
     counselling
    -0.82
     paed
    -0.80
     QC
    -0.78
     glim
    -0.78
    âĶĢâĶĢ
    -0.75
    vic
    -0.74
    POSITIVE LOGITS
     America
    1.64
    America
    1.51
     AMERICA
    1.49
     American
    1.49
     Americans
    1.48
    Americans
    1.43
     USA
    1.32
     AMER
    1.31
     Washington
    1.30
     Barack
    1.26
    Activations Density 0.653%

    No Known Activations