© 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. 4825
    Prev
    Next
    INDEX
    Explanations

    numeric patterns or sequences

    oai_token-act-pair · gpt-3.5-turbo
    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
    etimes
    -0.70
    Ward
    -0.62
    conservancy
    -0.57
    ITNESS
    -0.57
    chy
    -0.56
     Watts
    -0.56
     pressures
    -0.56
     PEOPLE
    -0.56
    sense
    -0.55
     rhet
    -0.55
    POSITIVE LOGITS
     onwards
    0.91
     onward
    0.89
    a
    0.76
    agall
    0.67
    isode
    0.64
    rio
    0.64
    ulhu
    0.63
    bis
    0.62
    hello
    0.61
    vati
    0.61
    Activations Density 0.092%

    No Known Activations