© 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. 0-RES-JB
    11. 5301
    Prev
    Next
    INDEX
    Explanations

    mentions of "The New Yorker"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "The New Yorker."

    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
     robots
    -0.72
     Dil
    -0.67
     tel
    -0.67
     Dell
    -0.65
     Robotics
    -0.64
     bet
    -0.64
     Tel
    -0.63
    irit
    -0.62
    HS
    -0.62
     Kron
    -0.62
    POSITIVE LOGITS
     Yorker
    2.71
     Yorkers
    1.41
    iggle
    1.34
    timer
    1.31
     Observer
    1.02
    agogue
    0.98
     thoughtful
    0.94
    iddy
    0.93
     Nikki
    0.92
     Annie
    0.89
    Activations Density 0.045%

    No Known Activations