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. 6-RES-JB
    6. 21250
    Prev
    Next
    INDEX
    Explanations

    phrases related to American national interests

    oai_token-act-pair · gpt-3.5-turbo

    references to American interests and themes related to the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    epad
    -0.79
    »Ĵ
    -0.77
    hid
    -0.77
    hots
    -0.77
    ription
    -0.76
    actionDate
    -0.75
    icter
    -0.74
    quad
    -0.73
    linger
    -0.70
    LOD
    -0.70
    POSITIVE LOGITS
     citizens
    1.07
     democracy
    1.07
     taxpayers
    1.07
     territory
    1.03
     shores
    1.01
     society
    1.01
     sovereignty
    1.01
     policymakers
    0.99
     soil
    0.94
     institutions
    0.93
    Activations Density 0.190%

    No Known Activations