© 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. 14474
    Prev
    Next
    INDEX
    Explanations

    the name 'Teresa'

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Teresa

    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
     Sabha
    -0.74
     Dys
    -0.74
     Lans
    -0.71
    ropolitan
    -0.69
     Rumble
    -0.65
    reys
    -0.64
    âĻ
    -0.63
     recess
    -0.63
     hooks
    -0.62
    EStreamFrame
    -0.61
    POSITIVE LOGITS
     Teresa
    1.13
    uala
    0.86
    lli
    0.81
     convent
    0.75
    esan
    0.75
    ela
    0.74
    Cert
    0.74
    ablo
    0.74
    eln
    0.73
    uction
    0.73
    Activations Density 0.031%

    No Known Activations