© 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. 10-RES-JB
    11. 16553
    Prev
    Next
    INDEX
    Explanations

    verbs related to controlling or managing processes or organizations

    oai_token-act-pair · gpt-3.5-turbo

    actions related to control and leadership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lenin
    -0.70
    repre
    -0.61
    alam
    -0.60
    henko
    -0.60
    Bron
    -0.60
     RELEASE
    -0.60
    Ë
    -0.59
    grave
    -0.58
    shapeshifter
    -0.58
    Render
    -0.57
    POSITIVE LOGITS
    escape
    1.00
     af
    0.98
    aways
    0.95
     rampant
    0.91
    nin
    0.82
    ways
    0.80
    gs
    0.79
     simulations
    0.77
     smoothly
    0.76
    nell
    0.75
    Activations Density 0.034%

    No Known Activations