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. 19228
    Prev
    Next
    INDEX
    Explanations

    references to historical events related to battles and cities

    oai_token-act-pair · gpt-3.5-turbo

    references to ancient cultures and their mythologies

    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
     VIDEO
    -0.83
     fluorescent
    -0.83
     FAC
    -0.81
     SPORTS
    -0.79
     stickers
    -0.78
     bandwagon
    -0.77
     endorsements
    -0.75
     emergency
    -0.74
     PHOTO
    -0.74
     draft
    -0.73
    POSITIVE LOGITS
    anus
    1.42
    aea
    1.38
    aeus
    1.37
    asus
    1.35
    areth
    1.29
    rius
    1.27
    ocrates
    1.24
    idon
    1.24
    arius
    1.24
    ius
    1.21
    Activations Density 0.221%

    No Known Activations