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. 12760
    Prev
    Next
    INDEX
    Explanations

    keywords related to technology and specific technical terms

    oai_token-act-pair · gpt-3.5-turbo

    specific technical terms and proper nouns indicating products, functions, and features

    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
     Wyn
    -0.69
     glut
    -0.64
    ̶
    -0.63
    GBT
    -0.60
    \\\\\\\\
    -0.60
     unse
    -0.59
    âĢİ
    -0.59
     Brent
    -0.58
    vernment
    -0.58
     Fry
    -0.58
    POSITIVE LOGITS
     Accessories
    0.71
    workers
    0.69
    pedia
    0.69
    wrapper
    0.68
     Parables
    0.63
    milo
    0.63
     Definitions
    0.62
    owship
    0.62
    ILA
    0.62
    sonian
    0.61
    Activations Density 0.447%

    No Known Activations