© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 17821
    Prev
    Next
    INDEX
    Explanations

    apologies or expressions of regret

    oai_token-act-pair · gpt-3.5-turbo

    instances of apology or expressions of regret

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ranked
    -0.79
    tnc
    -0.74
    iltration
    -0.71
    arnaev
    -0.71
    irrel
    -0.69
    eele
    -0.68
    edience
    -0.68
    rouse
    -0.68
    psey
    -0.67
    minecraft
    -0.67
    POSITIVE LOGITS
     sorry
    1.08
     excuse
    0.92
    GES
    0.85
    sorry
    0.85
    Sorry
    0.80
     Sorry
    0.74
    giving
    0.73
     apologies
    0.72
    tm
    0.72
     Customers
    0.69
    Activations Density 0.014%

    No Known Activations