© 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. 3-RES-JB
    11. 16430
    Prev
    Next
    INDEX
    Explanations

    references to the OECD (Organization for Economic Cooperation and Development) in economic and statistical contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to international organizations related to economic and trade issues

    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
    flies
    -0.86
    packs
    -0.84
    pite
    -0.83
    fly
    -0.78
    geon
    -0.76
    hound
    -0.69
    sbm
    -0.69
    veland
    -0.68
    inx
    -0.67
    req
    -0.67
    POSITIVE LOGITS
     OECD
    1.06
    ECD
    0.85
    ICA
    0.79
    ICLE
    0.77
     Countries
    0.73
     Sabha
    0.72
    TA
    0.71
    IC
    0.69
     countries
    0.69
     Cooperation
    0.69
    Activations Density 0.008%

    No Known Activations