© 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. 7-RES-JB
    11. 20822
    Prev
    Next
    INDEX
    Explanations

    text separated by certain symbols such as dashes and underscores

    oai_token-act-pair · gpt-3.5-turbo

    punctuation or symbols used to indicate structure in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lling
    -0.67
     nurs
    -0.66
     deliber
    -0.66
     cradle
    -0.62
    ollar
    -0.60
     snowball
    -0.59
    inav
    -0.57
     clipping
    -0.57
     miscarriage
    -0.57
     synerg
    -0.57
    POSITIVE LOGITS
    */
    1.07
    *****
    0.91
     =================================================================
    0.86
    edit
    0.82
     ARTICLE
    0.81
    quote
    0.78
    Requirements
    0.78
    ---
    0.77
    export
    0.77
    -->
    0.76
    Activations Density 0.077%

    No Known Activations