© 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. 1-RES-JB
    11. 20444
    Prev
    Next
    INDEX
    Explanations

    words related to a specific place or location

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Prince" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    asing
    -0.78
    hovah
    -0.75
     Vaugh
    -0.72
     Antar
    -0.72
    endi
    -0.71
    anwhile
    -0.70
     [+
    -0.70
    HUD
    -0.69
    alde
    -0.68
     Norn
    -0.68
    POSITIVE LOGITS
    cipled
    0.96
    pins
    0.89
    chest
    0.85
    haired
    0.81
    ches
    0.80
    cher
    0.77
     Prin
    0.77
    ching
    0.75
    ned
    0.75
     hypot
    0.75
    Activations Density 0.019%

    No Known Activations