© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 12435
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Lou" with varying activations, particularly focusing on instances where the name is prominently featured

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Lou" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Constructed
    -0.85
    flies
    -0.73
    ãģĨ
    -0.69
     CoC
    -0.66
     Tactics
    -0.65
     fences
    -0.64
    ansas
    -0.62
     fence
    -0.62
    Demand
    -0.62
    ãĥķ
    -0.61
    POSITIVE LOGITS
    vre
    1.24
     Geh
    1.01
    ving
    0.91
    illard
    0.88
    ochet
    0.88
    rie
    0.87
    zzy
    0.85
    lette
    0.84
    der
    0.83
    utenant
    0.81
    Activations Density 0.034%

    No Known Activations