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. 3533
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people, places, or events

    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
     heightened
    -0.61
     Patriots
    -0.60
     Buffett
    -0.60
     carefully
    -0.60
     millennial
    -0.59
     odds
    -0.58
     contingency
    -0.58
     Millenn
    -0.58
     taped
    -0.57
     purposefully
    -0.57
    POSITIVE LOGITS
    ona
    1.00
    ande
    1.00
    én
    0.99
    acha
    0.98
    ulla
    0.97
    uni
    0.95
    akh
    0.95
    una
    0.94
    acia
    0.94
    agh
    0.93
    Activations Density 0.517%

    No Known Activations