© 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. 4-RES-JB
    11. 10612
    Prev
    Next
    INDEX
    Explanations

    IT-related terms with the abbreviation "BI" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    references to "Building Information Modeling" (BIM) in various contexts

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

    No Comments

    Negative Logits
    lain
    -0.89
    ional
    -0.72
    isting
    -0.69
    bilt
    -0.68
     sands
    -0.66
    izers
    -0.64
     Uni
    -0.64
    lessness
    -0.62
    inho
    -0.60
    rooms
    -0.58
    POSITIVE LOGITS
    Īè
    0.95
    ī
    0.90
    ĨĴ
    0.87
    BI
    0.87
    bey
    0.83
    ļéĨĴ
    0.81
    undo
    0.80
    KER
    0.79
    ĸļ
    0.78
    ´
    0.78
    Activations Density 0.006%

    No Known Activations