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

    Neuronpedia

    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. 4-RES-JB
    11. 10602
    Prev
    Next
    INDEX
    Explanations

    instances related to negative emotions like guilt and remorse

    oai_token-act-pair · gpt-3.5-turbo

    terms related to guilt and remorse

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

    No Comments

    Negative Logits
    66666666
    -0.71
    andel
    -0.71
    chan
    -0.69
     Occupations
    -0.68
    psey
    -0.67
    IPS
    -0.62
    989
    -0.62
    IFE
    -0.61
    acers
    -0.61
    POL
    -0.61
    POSITIVE LOGITS
    lessness
    0.95
     guilt
    0.94
    less
    0.88
    fully
    0.87
    lessly
    0.85
    fulness
    0.81
     conscience
    0.78
    iness
    0.77
    worthiness
    0.77
    otine
    0.74
    Activations Density 0.012%

    No Known Activations