© 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. 4435
    Prev
    Next
    INDEX
    Explanations

    keywords indicating deadlines or scheduled events

    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
    sav
    -0.79
    zee
    -0.67
    sol
    -0.67
    rosso
    -0.63
    ski
    -0.59
    lean
    -0.58
    aving
    -0.57
    technology
    -0.57
    spir
    -0.57
    Ire
    -0.56
    POSITIVE LOGITS
     diligence
    0.92
    lling
    0.89
    lled
    0.79
     to
    0.76
    geries
    0.73
    iments
    0.70
    encing
    0.69
    enced
    0.68
    iment
    0.66
    uary
    0.66
    Activations Density 0.024%

    No Known Activations