© 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 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. 11-RES-JB
    11. 14660
    Prev
    Next
    INDEX
    Explanations

    words related to the term "Que" used in various contexts, potentially referencing the province of Quebec or other related entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "queer" and its derivatives

    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
     TODAY
    -0.71
    lessly
    -0.65
     OD
    -0.62
    baugh
    -0.62
     Sonic
    -0.60
    ronic
    -0.60
    ior
    -0.58
    FTWARE
    -0.57
     Wald
    -0.56
     owl
    -0.56
    POSITIVE LOGITS
    erness
    1.43
    uing
    1.12
    bec
    1.07
    ued
    1.07
    ues
    1.05
    zon
    1.03
    eny
    0.96
    yrinth
    0.93
    beck
    0.92
    erest
    0.90
    Activations Density 0.054%

    No Known Activations