© 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. 16936
    Prev
    Next
    INDEX
    Explanations

    mentions of Building Information Modeling (BIM) or related terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "BI," commonly associated with Building Information modeling or similar contexts

    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
    naire
    -0.88
    nery
    -0.70
    ional
    -0.70
    naires
    -0.65
    ishly
    -0.61
    lain
    -0.59
    afort
    -0.59
    property
    -0.58
    ochond
    -0.58
    ively
    -0.58
    POSITIVE LOGITS
    KER
    0.89
    RD
    0.83
    keye
    0.81
    wark
    0.81
    bles
    0.81
    RN
    0.79
    keley
    0.79
    EGIN
    0.79
    Īè
    0.78
    ļéĨĴ
    0.77
    Activations Density 0.053%

    No Known Activations