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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 13067
    Prev
    Next
    INDEX
    Explanations

    information related to political candidates, polling results, and election outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to electoral competition and polling data

    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
     respons
    -0.81
    ĸļ
    -0.80
     overload
    -0.79
     explorers
    -0.72
     CLSID
    -0.72
    obyl
    -0.71
     warranty
    -0.70
     censor
    -0.69
     warranties
    -0.69
    iquette
    -0.66
    POSITIVE LOGITS
     challenger
    1.13
    election
    1.06
     turnout
    1.04
     reelection
    1.01
    cand
    0.97
     majorities
    0.96
     voters
    0.95
     challengers
    0.95
     Elections
    0.95
     frontrunner
    0.92
    Activations Density 0.501%

    No Known Activations