© 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. 10-RES-JB
    11. 2643
    Prev
    Next
    INDEX
    Explanations

    apologies or instances of someone publicly expressing regret for their actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of public apologies

    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
    Downloadha
    -0.84
    corn
    -0.71
    arnaev
    -0.70
    aida
    -0.69
    uana
    -0.69
    weeney
    -0.68
    production
    -0.66
    tails
    -0.66
    adj
    -0.66
    eu
    -0.65
    POSITIVE LOGITS
     unres
    1.28
     apologized
    1.07
     apologize
    1.03
     sincerely
    1.02
     prof
    0.99
     apology
    0.97
    giving
    0.91
     apologise
    0.90
     apologizing
    0.90
     apologised
    0.90
    Activations Density 0.048%

    No Known Activations