© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 15465
    Prev
    Next
    INDEX
    Explanations

    the name "Lou"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Lou."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    java
    -0.74
    psc
    -0.74
     unprepared
    -0.71
    armac
    -0.68
    ahime
    -0.68
     intercept
    -0.66
    rans
    -0.66
    android
    -0.64
     tablets
    -0.63
     è£ıç
    -0.63
    POSITIVE LOGITS
     Lou
    3.86
    Lou
    3.15
     Louie
    1.76
     Louise
    1.53
     lou
    1.47
     Laf
    1.27
     Rou
    1.25
     Scher
    1.15
     Nou
    1.14
     Madonna
    1.10
    Activations Density 0.012%

    No Known Activations