© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11271
    Prev
    Next
    INDEX
    Explanations

    references to the name "Tommy"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Tommy."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ortment
    -0.85
    iard
    -0.78
    creen
    -0.77
    ividual
    -0.77
    ity
    -0.74
    ators
    -0.72
    isec
    -0.72
    itative
    -0.72
    iants
    -0.71
    icted
    -0.70
    POSITIVE LOGITS
    oshenko
    0.84
     Hil
    0.82
    Bone
    0.81
     Trash
    0.79
     Wise
    0.75
     Caldwell
    0.74
     Tune
    0.73
    kn
    0.72
     Chong
    0.72
     Robinson
    0.69
    Activations Density 0.048%

    No Known Activations