© 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. 8-RES-JB
    11. 24340
    Prev
    Next
    INDEX
    Explanations

    scientific measurements or levels of substances present

    oai_token-act-pair · gpt-3.5-turbo

    references to varying levels of substances or conditions

    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
    rontal
    -0.77
    issance
    -0.66
    enegger
    -0.65
    ned
    -0.65
    nell
    -0.65
     indie
    -0.60
    apixel
    -0.59
    sov
    -0.59
    ctors
    -0.58
     genre
    -0.58
    POSITIVE LOGITS
     detectable
    0.89
    ilibrium
    0.79
    etting
    0.78
     concentrations
    0.77
     fluct
    0.75
     levels
    0.75
    baugh
    0.73
     readings
    0.72
     fluctuations
    0.70
    ynt
    0.70
    Activations Density 0.048%

    No Known Activations