© 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. 11-RES-JB
    11. 14948
    Prev
    Next
    INDEX
    Explanations

    names, specifically focusing on names ending in 'las' and 'Andreas'

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riter
    -0.83
    lance
    -0.81
    wards
    -0.78
    isite
    -0.77
    ished
    -0.76
    fare
    -0.75
    fecture
    -0.75
    ewitness
    -0.74
    lled
    -0.74
    lished
    -0.73
    POSITIVE LOGITS
    henko
    0.96
    andro
    0.91
    lav
    0.89
    andr
    0.88
    '
    0.87
    Magikarp
    0.87
     Kats
    0.85
     Maduro
    0.84
     Jere
    0.84
     Anton
    0.84
    Activations Density 0.081%

    No Known Activations