© 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. 2-RES-JB
    11. 14686
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to Japan and specific characters in the text

    oai_token-act-pair · gpt-3.5-turbo

    specific names and terms related to the context of "Naruto" and "Hokkaido."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ffen
    -0.79
    oaded
    -0.67
    isons
    -0.65
     wedge
    -0.65
    Feed
    -0.65
    feed
    -0.64
    ried
    -0.64
    eering
    -0.63
    rying
    -0.63
     Baird
    -0.62
    POSITIVE LOGITS
     Hok
    1.08
     Iw
    0.95
     Uz
    0.94
     Naruto
    0.90
    doms
    0.87
    çİĭ
    0.83
     Sasuke
    0.80
    agall
    0.78
    amaru
    0.75
    uden
    0.75
    Activations Density 0.019%

    No Known Activations