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. 8964
    Prev
    Next
    INDEX
    Explanations

    German words related to legal and political issues

    oai_token-act-pair · gpt-3.5-turbo

    specific names or references, likely related to individuals or entities

    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
     radius
    -0.63
     Andromeda
    -0.63
     females
    -0.62
     groom
    -0.61
     Wiggins
    -0.61
     learnt
    -0.60
    ulative
    -0.60
     Xue
    -0.59
     2018
    -0.59
     nurture
    -0.58
    POSITIVE LOGITS
    cht
    2.89
    plin
    1.32
    ryan
    1.28
    hend
    1.13
     Dempsey
    1.11
    fat
    1.10
    ffen
    0.99
    cham
    0.99
    conom
    0.98
     Yorkers
    0.98
    Activations Density 0.019%

    No Known Activations