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. 8331
    Prev
    Next
    INDEX
    Explanations

    references or instructions related to education, organization, and management

    oai_token-act-pair · gpt-3.5-turbo

    references to educational resources and academic support

    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
    ensional
    -0.79
    arnaev
    -0.68
     Canaver
    -0.67
    apeshifter
    -0.66
    lus
    -0.65
    exclusive
    -0.64
    rew
    -0.62
    uzzle
    -0.61
    emporary
    -0.61
    artisan
    -0.60
    POSITIVE LOGITS
     etc
    1.21
     è£ıè
    0.83
     blah
    0.77
    !).
    0.72
     heartbeat
    0.67
    !),
    0.66
     plat
    0.65
    )?
    0.64
     ect
    0.62
     loader
    0.61
    Activations Density 1.464%

    No Known Activations