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. 0-RES-JB
    6. 20672
    Prev
    Next
    INDEX
    Explanations

    references to online platforms like wikis and Wikipedia

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Wiki" or "Wikipedia"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Samson
    -0.77
    luster
    -0.74
     ringing
    -0.71
     Opportunity
    -0.67
    lled
    -0.67
    bath
    -0.67
     complementary
    -0.64
    acted
    -0.64
    period
    -0.64
     Ortiz
    -0.63
    POSITIVE LOGITS
    Wiki
    3.81
     Wiki
    3.21
    wiki
    3.04
    wik
    2.80
     wiki
    2.59
    Wik
    2.08
     wik
    1.83
     Wik
    1.80
    pedia
    1.78
    edia
    1.60
    Activations Density 0.029%

    No Known Activations