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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 1090
    Prev
    Next
    INDEX
    Explanations

    references to the name "Michelle"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Michelle Obama

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Raid
    -0.80
    sov
    -0.78
    aten
    -0.72
     cryptoc
    -0.68
     telesc
    -0.68
    atos
    -0.65
    ften
    -0.63
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.62
     Volks
    -0.62
     Dynamo
    -0.61
    POSITIVE LOGITS
     Michelle
    3.56
    Michelle
    3.00
     Michele
    1.85
     Melania
    1.80
     Stephanie
    1.54
     Sandra
    1.52
     Emma
    1.43
     Valerie
    1.42
     Alicia
    1.40
     Erica
    1.40
    Activations Density 0.019%

    No Known Activations