© 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. 10-RES-JB
    11. 18992
    Prev
    Next
    INDEX
    Explanations

    dates and locations in news reports

    oai_token-act-pair · gpt-3.5-turbo

    dates and locations mentioned in the text

    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
    Reloaded
    -0.72
     chairs
    -0.67
     ourselves
    -0.60
    76561
    -0.59
    Sund
    -0.58
     testers
    -0.56
    geist
    -0.56
     yourselves
    -0.55
    rite
    -0.54
     whiff
    -0.53
    POSITIVE LOGITS
     REUTERS
    0.94
     ©
    0.79
    FILE
    0.77
     FILE
    0.76
    ./
    0.72
     âĶ
    0.71
    UTERS
    0.69
     Courtesy
    0.66
     Photographer
    0.66
    window
    0.65
    Activations Density 0.033%

    No Known Activations