© 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. 2546
    Prev
    Next
    INDEX
    Explanations

    locations, particularly indicating directions such as northern or southern areas

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

    geographical locations or regions

    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
    20439
    -0.88
    nikov
    -0.81
    otive
    -0.80
    DragonMagazine
    -0.77
    rieved
    -0.76
    gage
    -0.76
    76561
    -0.75
    =-=-
    -0.75
    ÃįÃį
    -0.75
    CW
    -0.74
    POSITIVE LOGITS
     France
    1.11
     Siberia
    1.05
     Laos
    1.04
     England
    1.03
     Thailand
    1.03
     Nigeria
    1.03
     Tanzania
    1.01
     Italy
    0.99
     Kenya
    0.98
     Serbia
    0.97
    Activations Density 0.058%

    No Known Activations