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. 6-RES-JB
    6. 6769
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals, such as actors or authors

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly Baldwin and Kaufman

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arthed
    -0.80
    ifier
    -0.80
    sis
    -0.75
    ional
    -0.75
    ually
    -0.72
    ifiable
    -0.72
    arist
    -0.71
    uate
    -0.68
    arant
    -0.67
    EMBER
    -0.66
    POSITIVE LOGITS
    enegger
    0.80
     Sapp
    0.80
     AFB
    0.79
    fman
    0.76
     Baldwin
    0.76
     Downs
    0.76
     Nelson
    0.69
     Kaufman
    0.69
     Henderson
    0.67
     Fitzgerald
    0.67
    Activations Density 0.048%

    No Known Activations