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. 4-RES-JB
    6. 8369
    Prev
    Next
    INDEX
    Explanations

    uncommon characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    parts of documents that contain dates or references to significant events

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

    No Comments

    Negative Logits
    ©¶æ
    -0.78
    Ń·
    -0.76
     appe
    -0.68
     vet
    -0.67
    £ı
    -0.65
    ĺħ
    -0.65
    £
    -0.63
    Ĥª
    -0.63
    ishable
    -0.62
     Luthor
    -0.61
    POSITIVE LOGITS
    ================================================================
    0.93
    ³³³³
    0.83
    Introduced
    0.81
    -----------
    0.79
    Related
    0.74
    References
    0.74
    Arcade
    0.73
    Hel
    0.72
    AMP
    0.72
    Anyway
    0.72
    Activations Density 0.257%

    No Known Activations