© 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. 7-RES-JB
    11. 1439
    Prev
    Next
    INDEX
    Explanations

    currency amounts specified in euros

    oai_token-act-pair · gpt-3.5-turbo

    monetary values or amounts, particularly in euros

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.75
     Turtles
    -0.70
     Khe
    -0.70
    pta
    -0.69
    oted
    -0.68
    etsk
    -0.67
     Alley
    -0.65
    assium
    -0.65
     Flavoring
    -0.64
    hattan
    -0.63
    POSITIVE LOGITS
    £
    1.07
    Ëľ
    1.02
     âĤ¬
    0.99
    âĤ¬
    0.92
    USD
    0.84
    cos
    0.83
    $
    0.74
    HP
    0.74
     EUR
    0.74
    Ãī
    0.73
    Activations Density 0.017%

    No Known Activations