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. 21512
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Dem" followed by a numerical value of 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Dem" or variations related to it, likely indicating a focus on Democratic entities or individuals

    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
    WAYS
    -0.90
    glers
    -0.73
    ties
    -0.69
    renheit
    -0.65
     Indigo
    -0.65
    CLASSIFIED
    -0.64
    terness
    -0.62
     Wonderland
    -0.61
    Pull
    -0.60
     HMS
    -0.60
    POSITIVE LOGITS
    olition
    1.24
    agogue
    1.15
    eanor
    1.03
    ocrat
    1.00
    agog
    1.00
    onym
    0.94
    ographics
    0.93
    psey
    0.93
    ilit
    0.92
    otion
    0.90
    Activations Density 0.015%

    No Known Activations