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. 8682
    Prev
    Next
    INDEX
    Explanations

    names, specifically those related to places or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "opal" and related terms, suggesting it looks for mentions of gemstones or related subjects

    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
    FS
    -0.73
    qus
    -0.69
    CSS
    -0.66
    LI
    -0.66
    sort
    -0.65
     dare
    -0.65
     Hit
    -0.65
     Atlas
    -0.64
    ISM
    -0.63
    EX
    -0.62
    POSITIVE LOGITS
    opal
    3.79
    mary
    2.25
    aintain
    1.36
    oulder
    1.00
    cill
    0.98
    uala
    0.91
    romy
    0.87
    blems
    0.84
    ovember
    0.81
    lav
    0.77
    Activations Density 0.041%

    No Known Activations