© 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. 11-RES-JB
    11. 20530
    Prev
    Next
    INDEX
    Explanations

    dates and locations within news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to dates and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imens
    -0.63
     beck
    -0.56
    "},"
    -0.55
    ewater
    -0.54
    ibles
    -0.53
     congr
    -0.53
     Kappa
    -0.52
    igmatic
    -0.51
     reimb
    -0.51
    "},
    -0.49
    POSITIVE LOGITS
    MAN
    0.75
    ONDON
    0.62
     NEWS
    0.57
    PAR
    0.57
    Madison
    0.54
    BER
    0.53
    ATT
    0.52
    WASHINGTON
    0.52
     HUM
    0.52
    Published
    0.52
    Activations Density 0.125%

    No Known Activations