© 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. 10-RES-JB
    11. 8587
    Prev
    Next
    INDEX
    Explanations

    generic statements following a pattern, potentially related to advice or guiding principles

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize positive qualities or rules

    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
    jri
    -0.74
    gemony
    -0.67
    cape
    -0.64
     Himself
    -0.64
    eds
    -0.63
    uthor
    -0.61
    ruption
    -0.61
    eters
    -0.61
     vanquished
    -0.60
    hyde
    -0.60
    POSITIVE LOGITS
    enough
    1.10
    reads
    1.08
     example
    1.04
     ol
    1.03
    bye
    1.03
     reason
    1.00
    luck
    0.98
     Samar
    0.95
     approximation
    0.95
     luck
    0.93
    Activations Density 0.068%

    No Known Activations