© 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. 2302
    Prev
    Next
    INDEX
    Explanations

    words and phrases written in Swedish

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

    phrases related to freedom and personal expression

    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
     Boxing
    -0.79
     Crane
    -0.74
     Chavez
    -0.71
     Guerrero
    -0.71
     Mayweather
    -0.70
     Phillies
    -0.69
     Cincinnati
    -0.69
     CPC
    -0.68
     Cavaliers
    -0.65
     Floyd
    -0.65
    POSITIVE LOGITS
    å
    1.15
    ä
    1.05
     om
    0.94
     som
    0.92
    liga
    0.91
     kan
    0.91
    ikk
    0.90
    arna
    0.85
    vik
    0.84
    riks
    0.83
    Activations Density 0.107%

    No Known Activations