© 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. 8-RES-JB
    11. 10417
    Prev
    Next
    INDEX
    Explanations

    adjectives describing positive qualities or actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social responsibility and well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    famous
    -0.76
     nervously
    -0.76
     smelled
    -0.75
     unwittingly
    -0.73
    yip
    -0.73
    mere
    -0.73
    cule
    -0.72
    wreck
    -0.72
    note
    -0.71
    acular
    -0.71
    POSITIVE LOGITS
     outcomes
    1.05
     solutions
    1.02
     governance
    1.00
     communication
    0.96
     responses
    0.95
     transitions
    0.95
     relationships
    0.95
     environments
    0.93
     alternatives
    0.93
     decisions
    0.92
    Activations Density 0.273%

    No Known Activations