© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 15212
    Prev
    Next
    INDEX
    Explanations

    phrases related to public opinion polling

    oai_token-act-pair · gpt-3.5-turbo

    references to polling in the context of elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.96
     Leilan
    -0.91
    uria
    -0.88
    xual
    -0.74
     Flavoring
    -0.74
    ĸļ
    -0.73
    ModLoader
    -0.73
    íķ
    -0.73
    EngineDebug
    -0.72
     certs
    -0.71
    POSITIVE LOGITS
     polling
    1.18
     polls
    0.94
     elector
    0.86
     booths
    0.83
     clerk
    0.76
     stations
    0.76
     electors
    0.76
    sters
    0.75
     averages
    0.75
     voters
    0.74
    Activations Density 0.005%

    No Known Activations