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. 6035
    Prev
    Next
    INDEX
    Explanations

    names of a specific poet or poetry related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Poisson" in various contexts

    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
    owship
    -0.79
     Commodore
    -0.69
    ATIONAL
    -0.65
     EDITION
    -0.65
     narrator
    -0.64
    stood
    -0.63
     Monarch
    -0.62
    lain
    -0.61
     Transparency
    -0.61
    worthiness
    -0.61
    POSITIVE LOGITS
    pper
    1.22
    ppy
    1.13
    etry
    1.11
    pping
    1.10
    ppel
    1.06
    inters
    1.03
    pez
    1.03
    orer
    1.02
    zzo
    1.00
    oting
    0.99
    Activations Density 0.029%

    No Known Activations