© 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. 11-RES-JB
    11. 3414
    Prev
    Next
    INDEX
    Explanations

    politically related terms and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and events in Iraq

    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
     Wilde
    -1.03
     bunny
    -0.97
     Luigi
    -0.96
     Droid
    -0.96
     Butterfly
    -0.93
     Gmail
    -0.93
    chester
    -0.91
     crochet
    -0.91
     Etsy
    -0.88
     Wu
    -0.85
    POSITIVE LOGITS
     Iraqi
    2.18
     Baghdad
    2.17
     Iraqis
    2.06
    Iraq
    2.01
     Mosul
    1.96
     Saddam
    1.84
     Iraq
    1.83
     Kurdistan
    1.75
     Shiite
    1.72
     Kurdish
    1.67
    Activations Density 0.291%

    No Known Activations