© 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 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. 3-RES-JB
    11. 15
    Prev
    Next
    INDEX
    Explanations

    phrases related to international political affairs and agreements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "U.S." or its variants, particularly in contexts related to governance or international affairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dickinson
    -0.71
     TAMADRA
    -0.70
     PRO
    -0.70
     Madden
    -0.68
     McGr
    -0.67
    ersion
    -0.67
    xes
    -0.65
     Virt
    -0.64
     Cassidy
    -0.63
     Vapor
    -0.63
    POSITIVE LOGITS
    taboola
    1.11
    division
    0.95
    based
    0.87
    facing
    0.86
    _-
    0.85
    sized
    0.85
    tun
    0.84
    themed
    0.82
    san
    0.81
    generated
    0.81
    Activations Density 0.009%

    No Known Activations