© 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 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. 2042
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically focusing on locations or names

    oai_token-act-pair · gpt-3.5-turbo

    the name "Kun" and its various mentions in the context of military or strategic operations

    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
     tolerant
    -0.71
    prop
    -0.67
     acceptance
    -0.65
     cath
    -0.63
     prep
    -0.63
    rss
    -0.63
     olive
    -0.63
    expr
    -0.58
     adoption
    -0.58
     marg
    -0.57
    POSITIVE LOGITS
     Kun
    4.19
     Yun
    1.43
     Tsu
    1.34
     Kund
    1.33
     Kut
    1.31
     Kur
    1.25
     Kand
    1.21
    kun
    1.20
     Kub
    1.20
     Kahn
    1.17
    Activations Density 0.013%

    No Known Activations