© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 7410
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly with the name "Leonard"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Leonard."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.81
    exempt
    -0.81
    tch
    -0.80
    dule
    -0.77
    manship
    -0.75
    pron
    -0.72
    illance
    -0.70
    д
    -0.70
    yrim
    -0.70
    izons
    -0.70
    POSITIVE LOGITS
     Leonard
    1.00
     Lauder
    0.94
     Cohen
    0.88
    angelo
    0.84
    ardo
    0.84
     Strauss
    0.81
     Nim
    0.78
    ency
    0.76
     Gord
    0.72
     Hayward
    0.71
    Activations Density 0.037%

    No Known Activations