© 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. 9-RES-JB
    11. 8782
    Prev
    Next
    INDEX
    Explanations

    mentions of the German Chancellor Angela Merkel

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Angela Merkel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angular
    -0.84
    aped
    -0.80
     Iro
    -0.77
    apes
    -0.76
    arse
    -0.73
    aping
    -0.73
    nor
    -0.73
     Vaugh
    -0.70
    RECT
    -0.69
    avery
    -0.69
    POSITIVE LOGITS
     Merkel
    1.14
     herself
    0.96
    bach
    0.81
    issance
    0.80
    baum
    0.79
    mint
    0.76
     confid
    0.74
     Chancellor
    0.73
     chancellor
    0.70
    icial
    0.70
    Activations Density 0.043%

    No Known Activations