© 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. 13660
    Prev
    Next
    INDEX
    Explanations

    mentions of celebrities

    oai_token-act-pair · gpt-3.5-turbo

    references to celebrities

    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
    anus
    -0.78
    iHUD
    -0.75
    ¾
    -0.73
    ^^^^
    -0.72
    edin
    -0.71
    etheless
    -0.68
    ²¾
    -0.68
    tered
    -0.67
    ulhu
    -0.67
    ¸
    -0.66
    POSITIVE LOGITS
     endors
    1.30
    rities
    1.26
     endorsements
    1.07
     gossip
    1.04
     chef
    1.04
     TMZ
    0.90
     celebrities
    0.89
     Celeb
    0.89
     chefs
    0.86
     celebrity
    0.86
    Activations Density 0.104%

    No Known Activations