© 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. 4328
    Prev
    Next
    INDEX
    Explanations

    words related to specific organizations or entities

    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
    ienced
    -0.82
    loo
    -0.81
    neys
    -0.69
    rosse
    -0.68
    iences
    -0.67
    tons
    -0.67
    lington
    -0.66
    inson
    -0.64
    ingham
    -0.62
     Mata
    -0.62
    POSITIVE LOGITS
    ACP
    1.12
    UFC
    1.01
    ZI
    1.01
    emonic
    1.00
    iversal
    0.92
    STAR
    0.92
    umeric
    0.91
    IS
    0.89
    guyen
    0.88
    FU
    0.88
    Activations Density 0.068%

    No Known Activations