© 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. 4-RES-JB
    11. 20739
    Prev
    Next
    INDEX
    Explanations

    names related to the name "Claire"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual named Claire

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

    No Comments

    Negative Logits
    awaru
    -0.87
    oppable
    -0.79
    oster
    -0.76
    alm
    -0.72
    udeb
    -0.70
    urtles
    -0.70
    odiac
    -0.69
    abad
    -0.68
    omy
    -0.67
    isconsin
    -0.67
    POSITIVE LOGITS
    font
    1.00
    mont
    0.94
     Clare
    0.91
     Bride
    0.88
     Mai
    0.86
     Claire
    0.86
    mere
    0.76
    bian
    0.74
     Elise
    0.73
     Lip
    0.72
    Activations Density 0.010%

    No Known Activations