© 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. 4242
    Prev
    Next
    INDEX
    Explanations

    instances where someone is physically present in a specific location or event

    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
    angered
    -0.74
     spir
    -0.69
    selves
    -0.68
     belong
    -0.66
    cano
    -0.64
    ¯
    -0.64
    enment
    -0.64
     sake
    -0.64
    olitan
    -0.63
    types
    -0.61
    POSITIVE LOGITS
     Prague
    0.91
     Charlottesville
    0.84
     pains
    0.83
     Indianapolis
    0.81
     Cannes
    0.80
     Bahrain
    0.79
     Perth
    0.76
     town
    0.76
     Wichita
    0.75
     Sacramento
    0.75
    Activations Density 0.221%

    No Known Activations