© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 12711
    Prev
    Next
    INDEX
    Explanations

    mentions of leaders or individuals in positions of authority

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of leaders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pwr
    -0.77
    zl
    -0.72
     tan
    -0.66
    agra
    -0.66
    ork
    -0.66
    agon
    -0.65
     Fusion
    -0.64
    berra
    -0.64
    urious
    -0.63
    abb
    -0.63
    POSITIVE LOGITS
    boards
    0.98
    board
    0.94
    leader
    0.93
    esses
    0.87
    doms
    0.86
    pins
    0.84
    aroo
    0.83
    stration
    0.80
    wcs
    0.80
     leader
    0.79
    Activations Density 0.025%

    No Known Activations