© 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. 2557
    Prev
    Next
    INDEX
    Explanations

    references to pilot programs or instances where the word "pilot" is used in a non-aviation context

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

    references to pilot programs and related terminology

    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
    Brexit
    -0.71
    acity
    -0.63
    upon
    -0.62
    cano
    -0.61
     Kingdoms
    -0.61
    ulkan
    -0.60
    roots
    -0.60
    TOP
    -0.60
    llo
    -0.59
     Wrest
    -0.59
    POSITIVE LOGITS
    wings
    1.18
    cies
    1.00
    ing
    0.88
    els
    0.86
    cy
    0.85
    ships
    0.79
     episode
    0.78
    istic
    0.76
     whales
    0.76
     flying
    0.74
    Activations Density 0.082%

    No Known Activations