© 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. 11-RES-JB
    11. 7572
    Prev
    Next
    INDEX
    Explanations

    verbs related to leading, such as "lead," "leading," and "led."

    oai_token-act-pair · gpt-3.5-turbo

    references to leadership or leading individuals and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.61
    iddler
    -0.57
     Sharing
    -0.57
    _____
    -0.56
    Trust
    -0.55
    aryn
    -0.54
    wa
    -0.52
     behold
    -0.52
    text
    -0.52
     ILCS
    -0.52
    POSITIVE LOGITS
    ership
    0.94
     efforts
    0.87
     tours
    0.86
     chants
    0.85
     us
    0.83
     discussions
    0.77
    urous
    0.71
     conversations
    0.70
     inquiries
    0.69
    gers
    0.69
    Activations Density 0.051%

    No Known Activations