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. 24314
    Prev
    Next
    INDEX
    Explanations

    exclamations or expressions of surprise/emphasis

    oai_token-act-pair · gpt-3.5-turbo

    expressions of frustration or emphasis

    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
     Edit
    -0.71
    cv
    -0.63
    onial
    -0.62
    _
    -0.59
    ./
    -0.59
    º
    -0.59
     princip
    -0.59
    na
    -0.58
    isite
    -0.56
     estates
    -0.55
    POSITIVE LOGITS
     heck
    4.30
     hell
    1.98
     Heck
    1.61
     HELL
    1.45
     boo
    1.35
     sucker
    1.21
     darn
    1.20
     crap
    1.12
     fuck
    1.02
     kidding
    0.94
    Activations Density 0.014%

    No Known Activations