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. 10-RES-JB
    6. 10893
    Prev
    Next
    INDEX
    Explanations

    mentions of the phrase "state-of-the-art" followed by a specific noun

    oai_token-act-pair · gpt-3.5-turbo

    references to state-of-the-art technology or equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zup
    -0.82
    idious
    -0.71
    IPS
    -0.70
    isson
    -0.70
    illon
    -0.63
    ihar
    -0.60
    owicz
    -0.60
    RESULTS
    -0.59
    ioch
    -0.59
    BIL
    -0.59
    POSITIVE LOGITS
     art
    1.07
     affairs
    0.83
     world
    0.78
     matter
    0.75
    art
    0.75
     nation
    0.75
     universe
    0.73
     Union
    0.67
     emergency
    0.65
     artist
    0.65
    Activations Density 0.028%

    No Known Activations