© 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. 1-RES-JB
    11. 5337
    Prev
    Next
    INDEX
    Explanations

    mentions or variants of the word "eur" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the term 'euro' and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Solitaire
    -0.78
    BY
    -0.69
    corn
    -0.68
    Spot
    -0.66
    ****************
    -0.63
     LINE
    -0.63
    AY
    -0.61
     Wick
    -0.61
     Snap
    -0.61
     Prescott
    -0.61
    POSITIVE LOGITS
    eur
    1.38
    ldom
    1.02
    izons
    0.95
    geoning
    0.93
    istic
    0.88
    mares
    0.88
    naire
    0.86
    atus
    0.85
    ignty
    0.84
    emate
    0.82
    Activations Density 0.007%

    No Known Activations