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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 17527
    Prev
    Next
    INDEX
    Explanations

    names related to McDonnell or variations of it, and words related to miscarriage

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or entities, particularly related to the name McDonnell

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

    No Comments

    Negative Logits
    unin
    -0.75
     Flavoring
    -0.71
    tered
    -0.70
    ku
    -0.69
    bos
    -0.68
    tta
    -0.67
    ught
    -0.65
    ologically
    -0.65
     Lisbon
    -0.65
    och
    -0.64
    POSITIVE LOGITS
    Donnell
    1.03
    fman
    0.91
     McDonnell
    0.84
    issance
    0.83
     Douglas
    0.78
    è»
    0.77
    INGTON
    0.77
    ragon
    0.77
    rats
    0.76
    sburg
    0.73
    Activations Density 0.010%

    No Known Activations