© 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. 16981
    Prev
    Next
    INDEX
    Explanations

    apologies and expressions of regret

    oai_token-act-pair · gpt-3.5-turbo

    expressions of apology and regret

    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
     mosqu
    -0.85
    population
    -0.79
    unin
    -0.75
     monop
    -0.73
     density
    -0.70
    rones
    -0.70
     Locations
    -0.69
     Sear
    -0.69
    nergy
    -0.68
    Residents
    -0.68
    POSITIVE LOGITS
     apology
    2.06
     apologise
    2.05
     apologized
    2.00
     apologised
    1.99
     apologize
    1.94
     apologies
    1.90
     regrets
    1.85
     remorse
    1.81
     apologizing
    1.79
     regret
    1.78
    Activations Density 0.631%

    No Known Activations