Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23545
    Prev
    Next
    INDEX
    Explanations

    words written in Spanish, specifically focusing on words with accents and special characters

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases with diacritical marks or special characters, particularly in Spanish

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ashes
    -0.62
    ORED
    -0.60
     many
    -0.60
    ++++
    -0.59
     interstate
    -0.57
    reading
    -0.56
     Eleven
    -0.56
     Canterbury
    -0.56
     fry
    -0.56
     Classics
    -0.55
    POSITIVE LOGITS
    rio
    1.36
    ctica
    1.06
    ndum
    1.05
    rez
    1.03
    ð
    1.01
    ÃįÃį
    0.99
    dra
    0.98
    lio
    0.98
    lic
    0.98
    mite
    0.97
    Activations Density 0.042%

    No Known Activations