© 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. 0-RES-JB
    11. 2717
    Prev
    Next
    INDEX
    Explanations

    apologies and expressions of regret

    oai_token-act-pair · gpt-3.5-turbo

    expressions of apology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teenth
    -0.65
    TV
    -0.64
    imb
    -0.61
    inct
    -0.61
     Tow
    -0.59
    rowth
    -0.59
    Ess
    -0.59
    Block
    -0.58
    ier
    -0.58
    ur
    -0.57
    POSITIVE LOGITS
     sorry
    3.78
    sorry
    2.46
     Sorry
    1.96
    Sorry
    1.75
     apologies
    1.68
     apologise
    1.63
     apologize
    1.43
     glad
    1.38
     apology
    1.28
     ashamed
    1.26
    Activations Density 0.011%

    No Known Activations