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

    Neuronpedia

    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. 8-RES-JB
    11. 6965
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or code snippets containing mathematical operations

    oai_token-act-pair · gpt-3.5-turbo

    assignment or declaration statements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.84
    mercial
    -0.77
    liv
    -0.75
    ivia
    -0.72
    tainment
    -0.72
    soDeliveryDate
    -0.70
    itant
    -0.70
    tackle
    -0.70
    Mex
    -0.69
    ngth
    -0.69
    POSITIVE LOGITS
     [];
    1.18
     {}
    1.04
     nil
    0.97
     NULL
    0.91
     null
    0.90
     $(
    0.87
    ========
    0.84
    ============
    0.84
     False
    0.83
     {
    0.82
    Activations Density 0.021%

    No Known Activations