© 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. 10710
    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
    kefeller
    -0.91
    DragonMagazine
    -0.67
    otic
    -0.64
    rients
    -0.63
     redevelopment
    -0.63
    ison
    -0.63
    CLUS
    -0.62
    ESCO
    -0.62
     Fitness
    -0.61
    ready
    -0.61
    POSITIVE LOGITS
     inconvenience
    1.28
     inconven
    1.19
     offended
    1.05
     interruption
    1.00
     misled
    0.95
     typo
    0.92
     inaccur
    0.91
    mist
    0.91
     mistakes
    0.90
     inadvertently
    0.89
    Activations Density 0.120%

    No Known Activations