© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 4844
    Prev
    Next
    INDEX
    Explanations

    references to battles and defenses in a fantasy-themed context

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to specific characters and their actions in the "Game of Thrones" series

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    uckland
    -0.95
    Gaza
    -0.84
    taboola
    -0.78
     Tacoma
    -0.77
    awei
    -0.77
     Navajo
    -0.72
    gypt
    -0.71
     Reincarn
    -0.71
    Alien
    -0.70
    bestos
    -0.70
    POSITIVE LOGITS
     Bolton
    0.96
     Lann
    0.94
    wy
    0.90
     Landing
    0.88
    finger
    0.88
    jen
    0.81
     Targ
    0.80
     Robb
    0.78
     Frey
    0.77
    jon
    0.75
    Activations Density 0.088%

    No Known Activations