© 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 EvalsExportsAPI 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. 11-RES-JB
    11. 7453
    Prev
    Next
    INDEX
    Explanations

    phrases related to software functionality, specifically the ability to perform specific tasks with technological tools

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the presence of tools or methods associated with actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quez
    -0.82
    estate
    -0.79
    ulet
    -0.72
     Industries
    -0.69
    sburg
    -0.69
    fest
    -0.68
    insula
    -0.67
    WHERE
    -0.67
    bridge
    -0.65
    stre
    -0.65
    POSITIVE LOGITS
     impunity
    1.80
     ease
    1.62
     minimal
    1.38
    stood
    1.23
     regard
    1.14
     regards
    1.12
    draw
    1.11
     utmost
    1.09
     dignity
    1.07
     respect
    1.07
    Activations Density 0.187%

    No Known Activations