© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 4203
    Prev
    Next
    INDEX
    Explanations

    instances of people or characters appearing in various contexts or locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dp
    -0.77
    brid
    -0.69
    bidden
    -0.63
    aign
    -0.62
    rpm
    -0.61
    raft
    -0.61
    kos
    -0.61
    ses
    -0.61
     VK
    -0.61
    ced
    -0.60
    POSITIVE LOGITS
     onstage
    0.93
     alongside
    0.73
     briefly
    0.72
     poised
    0.71
     prominently
    0.70
    ãĤ¤ãĥĪ
    0.70
    vind
    0.69
     theat
    0.67
    éĹ
    0.64
     on
    0.64
    Activations Density 0.056%

    No Known Activations