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. 11-RES-JB
    6. 22376
    Prev
    Next
    INDEX
    Explanations

    percentages or fractions in the context of votes or electoral results

    oai_token-act-pair · gpt-3.5-turbo

    statistical data related to voting percentages and electoral outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assetsadobe
    -0.97
    eday
    -0.67
    Management
    -0.65
    ORGE
    -0.64
    rame
    -0.62
    ogy
    -0.61
    study
    -0.61
    spir
    -0.61
    Template
    -0.61
    traumatic
    -0.61
    POSITIVE LOGITS
     votes
    1.60
     delegates
    1.32
     ballots
    1.24
     vote
    1.23
     seats
    1.17
     Votes
    1.15
     voters
    1.13
     endorsements
    1.09
     pledged
    1.07
    legates
    1.03
    Activations Density 0.165%

    No Known Activations