© 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. 1-RES-JB
    11. 2123
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific organization, specifically "Murabaha."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Mur" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prometheus
    -0.75
     Primal
    -0.72
     OECD
    -0.70
     Fundamental
    -0.68
     Discord
    -0.67
    ISM
    -0.67
     CFR
    -0.64
     Bermuda
    -0.64
     Beyond
    -0.63
     Bayer
    -0.63
    POSITIVE LOGITS
    mur
    1.22
    ascus
    1.01
    thur
    0.96
     Mur
    0.93
    geon
    0.92
    rats
    0.90
    abit
    0.89
    daq
    0.88
     cumbers
    0.88
    querque
    0.88
    Activations Density 0.004%

    No Known Activations