© 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. 13064
    Prev
    Next
    INDEX
    Explanations

    names of individuals who are known for specific attributes or achievements, such as roles in movies, controversial political commentary, or certain talents

    oai_token-act-pair · gpt-3.5-turbo

    elements related to fame and recognition within a person's achievements or characteristics

    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
     NOTICE
    -0.81
    Disclaimer
    -0.79
    Reviewed
    -0.79
    eva
    -0.75
    >:
    -0.75
    andum
    -0.74
    another
    -0.73
    Materials
    -0.72
    foundation
    -0.72
    GROUP
    -0.72
    POSITIVE LOGITS
     stunts
    1.29
     antics
    1.17
     flashy
    1.16
     witty
    1.07
     fiery
    1.04
     quirky
    1.04
     outlandish
    1.03
     colourful
    0.97
     colorful
    0.97
     partying
    0.96
    Activations Density 0.411%

    No Known Activations