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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 16437
    Prev
    Next
    INDEX
    Explanations

    instances of apologies or demands for apologies

    oai_token-act-pair · gpt-3.5-turbo

    instances of apologies 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 @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jun
    -0.87
    weeney
    -0.85
    spot
    -0.80
    marked
    -0.74
    corn
    -0.74
    tail
    -0.71
    arnaev
    -0.68
    tails
    -0.68
    picking
    -0.66
    cop
    -0.65
    POSITIVE LOGITS
     apologize
    1.28
     apologized
    1.19
     apologise
    1.15
     apologised
    1.13
     apologizing
    1.09
     apology
    1.08
     apologies
    1.06
     sorry
    0.90
     apolog
    0.87
     pardon
    0.83
    Activations Density 0.010%

    No Known Activations