© 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. 10-RES-JB
    11. 13940
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals, particularly the name "Warren" with varying strengths of activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Warren."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dayName
    -0.87
    pmwiki
    -0.78
    lies
    -0.74
    netflix
    -0.73
    ãĤ´ãĥ³
    -0.71
    liness
    -0.70
    etheless
    -0.65
    cific
    -0.65
    odic
    -0.64
    ly
    -0.64
    POSITIVE LOGITS
     Buffett
    1.41
    sburg
    1.12
     Farrell
    0.96
    rade
    0.91
     Sapp
    0.91
     Harding
    0.89
     Buff
    0.86
     Warren
    0.83
    shire
    0.77
     Burger
    0.76
    Activations Density 0.027%

    No Known Activations