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. 3-RES-JB
    6. 11596
    Prev
    Next
    INDEX
    Explanations

    proper nouns or phrases related to specific places, organizations, or people

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gaming and significant negative actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Palest
    -0.69
     fluor
    -0.66
     vouchers
    -0.65
    EStream
    -0.64
     TAM
    -0.62
     boycot
    -0.61
     expend
    -0.57
     Charlottesville
    -0.56
     Rico
    -0.56
     isol
    -0.55
    POSITIVE LOGITS
    opsis
    0.67
    ean
    0.66
     Brothers
    0.65
    itty
    0.65
    ake
    0.65
    sounding
    0.65
    brew
    0.63
    utions
    0.62
    ilib
    0.62
    oot
    0.62
    Activations Density 0.369%

    No Known Activations