© 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. 1-RES-JB
    11. 3585
    Prev
    Next
    INDEX
    Explanations

    names starting or ending with "Marie"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Marie" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oted
    -0.78
    orage
    -0.78
    itious
    -0.74
    otional
    -0.74
    ORE
    -0.72
    ainment
    -0.70
    raints
    -0.69
    olding
    -0.68
    recomm
    -0.68
    andals
    -0.68
    POSITIVE LOGITS
     Claire
    1.00
     Marie
    0.98
    lette
    0.90
    Marie
    0.89
     Slaughter
    0.84
     Louise
    0.82
    lla
    0.82
     mosqu
    0.77
    bilt
    0.76
    theless
    0.70
    Activations Density 0.003%

    No Known Activations