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. 3-RES-JB
    6. 14961
    Prev
    Next
    INDEX
    Explanations

    names and titles with accents and special characters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to digital systems or programming errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ernels
    -0.77
    ukong
    -0.74
    wcs
    -0.74
    generated
    -0.71
    blogs
    -0.70
    Premium
    -0.68
     satell
    -0.68
    akedown
    -0.66
    untled
    -0.65
     readable
    -0.64
    POSITIVE LOGITS
    ée
    1.04
    rique
    0.97
    é
    0.94
     Ãī
    0.92
    ç
    0.86
    Ãł
    0.86
    ó
    0.85
    Ãī
    0.84
    én
    0.84
    Ã
    0.83
    Activations Density 0.228%

    No Known Activations