© 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. 10-RES-JB
    11. 3439
    Prev
    Next
    INDEX
    Explanations

    dates mentioned in news articles

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "On" followed by a date or time reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cutter
    -0.69
    ãĤ£
    -0.63
    soDeliveryDate
    -0.62
    Export
    -0.57
    illac
    -0.57
     respectively
    -0.56
    inventoryQuantity
    -0.56
    oother
    -0.55
    perse
    -0.55
     damned
    -0.54
    POSITIVE LOGITS
    slaught
    1.32
     behalf
    1.17
     September
    1.08
     July
    1.06
     October
    1.04
     occasion
    1.03
     January
    1.03
     February
    1.03
     Wednesday
    1.02
    yx
    1.02
    Activations Density 0.038%

    No Known Activations