© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16035
    Prev
    Next
    INDEX
    Explanations

    words related to agreements or contracts

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "ag" in various contexts, possibly indicating focus on agricultural or related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parenthood
    -0.76
     defendant
    -0.64
    theless
    -0.64
     nomine
    -0.64
     comma
    -0.62
     hem
    -0.61
    éĹĺ
    -0.61
     stead
    -0.59
     Piper
    -0.59
     pepper
    -0.59
    POSITIVE LOGITS
    reement
    1.14
    ogo
    1.07
    gers
    1.06
    raf
    1.04
    reements
    1.04
    agging
    1.03
    gress
    1.02
    hetto
    1.00
    azine
    0.99
    gy
    0.99
    Activations Density 0.015%

    No Known Activations