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. 8-RES-JB
    6. 6717
    Prev
    Next
    INDEX
    Explanations

    alphabetic strings containing a sequence of characters that resemble "ys", "art", "ves", "vest", "cy", "iser", "ars", or "ia"

    oai_token-act-pair · gpt-3.5-turbo

    words related to analysis and critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Volunteers
    -0.67
    raltar
    -0.63
    yip
    -0.60
    nington
    -0.59
     Shutterstock
    -0.58
     Donation
    -0.56
    æĸ¹
    -0.54
    rowd
    -0.54
     Revolution
    -0.53
     Mechdragon
    -0.53
    POSITIVE LOGITS
    ctor
    0.69
    istics
    0.68
    ements
    0.67
    cipline
    0.65
    ement
    0.65
    aning
    0.64
    wig
    0.63
    umn
    0.62
    itten
    0.61
    itis
    0.60
    Activations Density 0.192%

    No Known Activations