© 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. 2-RES-JB
    11. 18856
    Prev
    Next
    INDEX
    Explanations

    articles about specific individuals, potentially related to personal or legal matters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Murabaha" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISM
    -0.76
     Pixie
    -0.73
     Fundamental
    -0.71
     Bermuda
    -0.71
     Gutenberg
    -0.70
     Devi
    -0.67
     Continued
    -0.66
     Sector
    -0.66
     Prometheus
    -0.66
     OECD
    -0.65
    POSITIVE LOGITS
    mur
    1.30
    daq
    0.96
    geon
    0.93
    rats
    0.92
    phies
    0.90
    nit
    0.87
    anda
    0.87
    der
    0.86
    ascus
    0.86
     Mur
    0.85
    Activations Density 0.007%

    No Known Activations