© 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. 21839
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases ending in a full stop (period)

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating a condition or quality

    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
     nomine
    -0.96
    plet
    -0.78
     magically
    -0.77
    reon
    -0.76
     questioning
    -0.72
     twent
    -0.71
    miah
    -0.70
    itage
    -0.70
     eleph
    -0.70
     right
    -0.69
    POSITIVE LOGITS
     Examples
    1.58
     Generally
    1.51
     Occasionally
    1.50
     Alternatively
    1.45
     Conversely
    1.44
     Therefore
    1.43
     Often
    1.43
     Typically
    1.43
     Typical
    1.43
     Depending
    1.42
    Activations Density 0.237%

    No Known Activations