© 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. 2-RES-JB
    11. 18809
    Prev
    Next
    INDEX
    Explanations

    the name "Nico" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly the names Nico and Sophie

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istas
    -0.79
    lamm
    -0.78
    ista
    -0.77
    scl
    -0.77
    natureconservancy
    -0.77
    oran
    -0.76
    interstitial
    -0.71
    ansas
    -0.70
    MpServer
    -0.70
    NING
    -0.70
    POSITIVE LOGITS
     Nico
    1.27
     Olivier
    0.93
     Gerard
    0.88
     Micha
    0.83
     Nicolas
    0.79
     Wilde
    0.76
     Hans
    0.76
    ë
    0.74
    lette
    0.70
     Brend
    0.70
    Activations Density 0.012%

    No Known Activations