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. 0-RES-JB
    6. 19720
    Prev
    Next
    INDEX
    Explanations

    names related to the surname "Wang" with variations of characters

    oai_token-act-pair · gpt-3.5-turbo

    the name "Wang" associated with significant mentions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acid
    -0.85
     Antar
    -0.74
     acid
    -0.74
     salts
    -0.74
    ement
    -0.71
    arrass
    -0.70
     insulin
    -0.70
     olig
    -0.69
     Orbit
    -0.68
     Malta
    -0.67
    POSITIVE LOGITS
     Wang
    2.32
     Wendy
    1.69
     CW
    1.65
    CW
    1.61
     Wad
    1.61
    BW
    1.54
    Wan
    1.50
    W
    1.49
     Wor
    1.48
    WT
    1.47
    Activations Density 0.065%

    No Known Activations