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. 8262
    Prev
    Next
    INDEX
    Explanations

    political polling data and statistics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political candidates and their polling data

    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
    -0.79
    obyl
    -0.76
    Reviewed
    -0.74
    tenance
    -0.72
     Investig
    -0.69
     intrusive
    -0.67
    cms
    -0.67
    agate
    -0.66
     EntityItem
    -0.66
    eval
    -0.62
    POSITIVE LOGITS
     majorities
    1.37
     landslide
    1.29
     plurality
    1.22
     margin
    1.17
     victories
    1.15
     margins
    1.14
     victory
    1.13
     electoral
    1.12
     landsl
    1.12
     Electoral
    1.11
    Activations Density 0.253%

    No Known Activations