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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 23680
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions or findings from polls or surveys

    oai_token-act-pair · gpt-3.5-turbo

    statements related to public opinion surveys and polling data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     laundering
    -0.77
     docking
    -0.77
     scal
    -0.76
     gou
    -0.74
     leased
    -0.71
     wre
    -0.71
     Artemis
    -0.69
     graft
    -0.68
    ombo
    -0.68
    aundering
    -0.67
    POSITIVE LOGITS
     majorities
    1.53
     Gallup
    1.31
     polled
    1.29
     respondents
    1.18
     Pew
    1.13
     survey
    1.04
     surveyed
    1.03
     poll
    1.02
     undecided
    1.00
     Rasmussen
    1.00
    Activations Density 0.564%

    No Known Activations