© 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. 7761
    Prev
    Next
    INDEX
    Explanations

    words related to setting examples or being a precedent

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss setting precedents or models for future actions and policies

    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
    aeus
    -0.81
    女
    -0.73
    igree
    -0.68
    omes
    -0.68
    ovych
    -0.67
    ifact
    -0.65
    heart
    -0.65
    leep
    -0.64
    Includes
    -0.63
    ettes
    -0.62
    POSITIVE LOGITS
     future
    1.55
     subsequent
    1.35
     others
    1.14
     eventual
    1.08
     aspiring
    1.05
     upcoming
    0.99
     other
    0.98
     further
    0.97
     later
    0.96
     broader
    0.95
    Activations Density 0.299%

    No Known Activations