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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 3883
    Prev
    Next
    INDEX
    Explanations

    words related to negative emotions like shame, guilt, pity, anger, and judgment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of shame and related emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enhagen
    -0.82
    ersive
    -0.79
    ichick
    -0.73
    agall
    -0.73
    ancial
    -0.72
    aeda
    -0.70
    IFE
    -0.69
    irements
    -0.68
    agnetic
    -0.67
    ighters
    -0.65
    POSITIVE LOGITS
    faced
    1.33
    fully
    1.30
    face
    1.00
    fulness
    0.99
    imaru
    0.97
    ously
    0.93
    ful
    0.93
     Shame
    0.90
     shame
    0.90
     judgement
    0.82
    Activations Density 0.044%

    No Known Activations