© 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. 2-RES-JB
    11. 19765
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific name "McMahan"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "McM."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glers
    -0.96
    GER
    -0.77
    ãĥį
    -0.75
    âĢİ
    -0.74
     Grateful
    -0.73
    gered
    -0.72
    ging
    -0.72
    gio
    -0.70
    gers
    -0.70
    ãĥ³ãĤ¸
    -0.68
    POSITIVE LOGITS
     McM
    0.88
    illian
    0.85
    Afee
    0.84
    essage
    0.83
     gobl
    0.83
     shenan
    0.81
    ovember
    0.81
    intosh
    0.81
     comr
    0.80
     unden
    0.80
    Activations Density 0.005%

    No Known Activations