© 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. 0-RES-JB
    11. 4807
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political figures named Kirchner

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those with the name "Kir."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Baltimore
    -0.69
    rome
    -0.69
    ungle
    -0.68
    engine
    -0.66
     overt
    -0.65
    adelphia
    -0.64
    MSN
    -0.63
    peed
    -0.62
    Factor
    -0.62
     Thanksgiving
    -0.61
    POSITIVE LOGITS
     Kir
    3.94
     Shir
    1.51
     Kur
    1.42
     Kik
    1.29
     Hir
    1.22
     Kyr
    1.20
     Kuro
    1.20
     Nish
    1.19
     Hik
    1.13
     Kis
    1.12
    Activations Density 0.010%

    No Known Activations