© 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. 11241
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically the last name "Sullivan"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Sullivan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    orian
    -0.88
    ancies
    -0.81
    aceous
    -0.79
    eon
    -0.78
    heid
    -0.78
    unal
    -0.78
    atical
    -0.76
    acent
    -0.74
    icles
    -0.74
    ATIONAL
    -0.74
    POSITIVE LOGITS
    ²¾
    0.69
     Soup
    0.69
     Hoo
    0.66
     Strait
    0.65
    vier
    0.65
    bach
    0.64
    issance
    0.62
    email
    0.61
    zman
    0.60
    geant
    0.59
    Activations Density 0.073%

    No Known Activations