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. 8743
    Prev
    Next
    INDEX
    Explanations

    references to microscopy-related terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms of microscopy and imaging techniques

    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
     ambassadors
    -0.74
     stal
    -0.65
     bell
    -0.65
     champion
    -0.65
     accord
    -0.63
     serving
    -0.62
     Domin
    -0.62
     ambassador
    -0.62
     Esp
    -0.61
     fel
    -0.60
    POSITIVE LOGITS
    opy
    4.59
    opic
    1.87
    oping
    1.43
    op
    1.34
    opsy
    1.28
    oped
    1.23
    omy
    1.21
    ogie
    1.16
    phy
    1.16
    ops
    1.13
    Activations Density 0.013%

    No Known Activations