© 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. 11-RES-JB
    11. 20471
    Prev
    Next
    INDEX
    Explanations

    text related to Mexican politics and events

    oai_token-act-pair · gpt-3.5-turbo

    specific letters or sequences that appear frequently in words related to governance or political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     lump
    -0.61
     liberals
    -0.59
     attachments
    -0.58
     Huff
    -0.56
     clutter
    -0.55
     gum
    -0.54
     clerks
    -0.54
     jew
    -0.54
    addons
    -0.53
     haw
    -0.53
    POSITIVE LOGITS
    rique
    1.17
    és
    1.13
    é
    1.12
    Ä
    1.11
    rica
    1.08
    ̶
    1.05
    ÃŃn
    1.05
    î
    1.04
    Ãł
    1.03
    ée
    1.03
    Activations Density 0.101%

    No Known Activations