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. 5251
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations, ownership, and business activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    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
    ESE
    -0.79
    these
    -0.73
    insk
    -0.71
    ievers
    -0.70
     refrain
    -0.67
    few
    -0.66
    ibel
    -0.65
    ¶
    -0.64
    ð
    -0.63
    iasco
    -0.62
    POSITIVE LOGITS
     downright
    0.83
     called
    0.72
     suppose
    0.70
     undoubtedly
    0.69
     probably
    0.68
     priceless
    0.68
     easier
    0.68
     gonna
    0.67
     definitely
    0.67
     tougher
    0.67
    Activations Density 0.212%

    No Known Activations