Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 24071
    Prev
    Next
    INDEX
    Explanations

    _mentions or references to "The New Yorker" publication

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "The New Yorker" publication

    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
    leading
    -0.73
    hold
    -0.73
    smoking
    -0.72
    etime
    -0.71
    ETA
    -0.70
    held
    -0.69
    road
    -0.68
    lower
    -0.67
    cause
    -0.67
    rams
    -0.66
    POSITIVE LOGITS
     Yorker
    0.97
    vier
    0.90
     Wire
    0.83
     Mellon
    0.81
     Magazine
    0.77
     magazine
    0.76
     Juda
    0.75
     Jacket
    0.73
     Swim
    0.72
    opol
    0.70
    Activations Density 0.010%

    No Known Activations