© 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. 8-RES-JB
    11. 6297
    Prev
    Next
    INDEX
    Explanations

    references to a specific name "Tommy"

    oai_token-act-pair · gpt-3.5-turbo

    mentions 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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iard
    -0.83
    places
    -0.81
    ortment
    -0.80
    agher
    -0.79
    ividual
    -0.78
    elaide
    -0.76
    ership
    -0.76
    idences
    -0.76
    ences
    -0.76
    ered
    -0.75
    POSITIVE LOGITS
     Hil
    0.87
     Trash
    0.84
     Robinson
    0.83
    oshenko
    0.81
    Bone
    0.77
     Caldwell
    0.76
    kn
    0.73
     DeV
    0.72
     Tune
    0.71
    my
    0.71
    Activations Density 0.030%

    No Known Activations