© 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. 11-RES-JB
    11. 11653
    Prev
    Next
    INDEX
    Explanations

    phrases related to email subscription requests

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibly
    -0.80
    onse
    -0.75
    hered
    -0.71
    FontSize
    -0.70
    iddling
    -0.69
    neutral
    -0.68
    iddled
    -0.67
     unsuccessfully
    -0.67
    stru
    -0.67
    ledged
    -0.65
    POSITIVE LOGITS
     latest
    1.22
     Recipe
    1.19
     Latest
    1.09
     hottest
    1.07
     scoop
    0.90
     BEST
    0.84
     best
    0.83
     Facts
    0.81
     411
    0.80
     facts
    0.80
    Activations Density 0.028%

    No Known Activations