© 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. 11320
    Prev
    Next
    INDEX
    Explanations

    the name "Den"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Den" or variations of it

    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
    inals
    -0.63
     grap
    -0.61
    enance
    -0.58
     feats
    -0.58
     insofar
    -0.57
     linking
    -0.57
     minded
    -0.56
     Stard
    -0.56
    heet
    -0.55
    LES
    -0.55
    POSITIVE LOGITS
    izens
    1.22
    zel
    1.22
    izen
    1.19
    omination
    1.18
    holm
    1.09
    omin
    1.06
    ouncing
    0.99
    isance
    0.96
    otes
    0.96
    ison
    0.95
    Activations Density 0.037%

    No Known Activations