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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 6553
    Prev
    Next
    INDEX
    Explanations

    the phrase "Poll" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to polling data or surveys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     XD
    -0.68
     ABE
    -0.66
    utical
    -0.66
    zos
    -0.65
    thood
    -0.63
    stan
    -0.63
     hacker
    -0.62
     experien
    -0.62
     las
    -0.62
    uni
    -0.61
    POSITIVE LOGITS
     Poll
    4.12
    Poll
    3.11
    poll
    2.64
     poll
    2.48
     polls
    1.84
     polling
    1.67
     polled
    1.24
     Survey
    1.21
     Ips
    1.20
     Voting
    1.20
    Activations Density 0.014%

    No Known Activations