Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 16837
    Prev
    Next
    INDEX
    Explanations

    information related to survey results and statistical data regarding political figures

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to polling and survey results

    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
    ĸļ
    -0.98
    assetsadobe
    -0.86
    £ı
    -0.84
    代
    -0.75
     recomp
    -0.75
    adr
    -0.74
    ertodd
    -0.74
    ciplinary
    -0.73
    ogical
    -0.70
    emis
    -0.69
    POSITIVE LOGITS
     frontrunner
    1.09
     majorities
    1.05
     Democrat
    1.04
     favorable
    1.02
     Hillary
    1.02
     Majority
    1.02
     undecided
    0.99
     Republicans
    0.99
    Republicans
    0.98
    avorable
    0.98
    Activations Density 0.238%

    No Known Activations