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

    Neuronpedia

    APICircuit 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. 2-RES-JB
    6. 8532
    Prev
    Next
    INDEX
    Explanations

    instances of the Swedish letter "å"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or symbol

    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
    cler
    -0.76
    agonist
    -0.72
    idepress
    -0.66
     entirety
    -0.65
     crush
    -0.64
    arily
    -0.63
    clerosis
    -0.63
    naires
    -0.63
     Hera
    -0.62
     carriers
    -0.61
    POSITIVE LOGITS
    å
    1.22
    ø
    0.94
    sson
    0.93
    ä
    0.90
    sb
    0.87
    ð
    0.85
    ö
    0.85
    ¢
    0.84
    borg
    0.84
    riks
    0.83
    Activations Density 0.003%

    No Known Activations