© 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. 8-RES-JB
    11. 10570
    Prev
    Next
    INDEX
    Explanations

    quantitative values typically associated with statistics or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical representations of statistics and metrics

    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
    redd
    -0.65
    ictions
    -0.58
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.58
    laim
    -0.57
     âĵĺ
    -0.57
    sale
    -0.56
    ffen
    -0.56
    Ĭ
    -0.55
    ionics
    -0.54
    also
    -0.53
    POSITIVE LOGITS
    %).
    0.92
    %)
    0.87
     equivalent
    0.84
    SOURCE
    0.71
    %),
    0.70
    enegger
    0.64
     cents
    0.63
    actly
    0.62
     multiplied
    0.61
     cubic
    0.61
    Activations Density 0.245%

    No Known Activations