© 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. 12-RES-JB
    11. 3231
    Prev
    Next
    INDEX
    Explanations

    texts discussing personal attributes, actions, and comparisons

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to political beliefs and the authenticity of political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     Navajo
    -0.95
     Honolulu
    -0.81
    outheast
    -0.78
     synchronized
    -0.77
     Hawai
    -0.77
     Hawaiian
    -0.77
    atl
    -0.76
     centers
    -0.76
    ijuana
    -0.73
     localized
    -0.72
    POSITIVE LOGITS
     Miliband
    1.85
     Labour
    1.75
     Corbyn
    1.71
     Tories
    1.71
     Tory
    1.69
    Labour
    1.65
     Thatcher
    1.64
     UKIP
    1.63
     Ukip
    1.62
     Cameron
    1.59
    Activations Density 0.616%

    No Known Activations