© 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. 10-RES-JB
    11. 18946
    Prev
    Next
    INDEX
    Explanations

    specific mentions of polling activities

    oai_token-act-pair · gpt-3.5-turbo

    references to polls and polling activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.91
     Classic
    -0.67
     GSL
    -0.66
     ultraviolet
    -0.66
     Melody
    -0.65
     Revel
    -0.65
     Journey
    -0.65
     Schwar
    -0.65
     Beard
    -0.63
     Poe
    -0.63
    POSITIVE LOGITS
    uting
    1.31
    sters
    1.26
    uters
    1.21
    inators
    1.20
    uted
    1.16
    inating
    1.12
    ution
    1.10
    ster
    1.09
    uter
    1.09
    inator
    1.07
    Activations Density 0.029%

    No Known Activations