© 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. 2-RES-JB
    11. 1487
    Prev
    Next
    INDEX
    Explanations

    words related to negative emotions like shame and remorse

    oai_token-act-pair · gpt-3.5-turbo

    expressions of shame and remorse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Trend
    -0.85
    tailed
    -0.77
    tails
    -0.76
    yip
    -0.72
    anto
    -0.66
    tail
    -0.63
    risome
    -0.63
    papers
    -0.62
    stakes
    -0.61
    ties
    -0.61
    POSITIVE LOGITS
     ashamed
    0.97
    xual
    0.95
     blush
    0.82
     cheeks
    0.76
     remorse
    0.75
    nikov
    0.71
    iates
    0.68
    leeve
    0.67
    ript
    0.67
    perture
    0.67
    Activations Density 0.022%

    No Known Activations