© 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. 12-RES-JB
    11. 3528
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns, especially focusing on possession and ownership

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to ownership and possession in the context of gameplay

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    vertisements
    -0.80
    iquette
    -0.76
    biz
    -0.73
    pole
    -0.71
    esson
    -0.69
    vell
    -0.68
    rose
    -0.68
    rupt
    -0.68
    Å¡
    -0.68
    vu
    -0.68
    POSITIVE LOGITS
     character
    1.08
     opponent
    1.04
     inventory
    1.01
     faction
    0.98
     Characters
    0.96
     Character
    0.95
     avatar
    0.93
     cursor
    0.93
     opponents
    0.92
     deck
    0.91
    Activations Density 0.177%

    No Known Activations