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. 22826
    Prev
    Next
    INDEX
    Explanations

    names of universities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly related to individuals and their roles

    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
     Flavoring
    -0.93
    Fort
    -0.82
     Nin
    -0.79
     Orioles
    -0.79
     Vietnam
    -0.78
     HI
    -0.72
     Nec
    -0.72
    mun
    -0.71
    iet
    -0.70
     Orc
    -0.69
    POSITIVE LOGITS
     Clarkson
    2.79
     Lambert
    2.40
     Chapman
    1.80
    camera
    1.39
     Schneider
    1.36
     Dickinson
    1.06
     Barker
    1.06
     Stam
    1.05
    addon
    1.04
    rake
    1.02
    Activations Density 0.066%

    No Known Activations