© 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. 2-RES-JB
    11. 15134
    Prev
    Next
    INDEX
    Explanations

    words related to envy or jealousy

    oai_token-act-pair · gpt-3.5-turbo

    terms and expressions related to jealousy

    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
     Medicare
    -0.70
     CPC
    -0.67
    ampunk
    -0.66
    Medic
    -0.66
     Afghanistan
    -0.64
    ARS
    -0.64
     TBD
    -0.63
     Taj
    -0.62
     Aleppo
    -0.62
    Downloadha
    -0.61
    POSITIVE LOGITS
    ealous
    1.06
    y
    0.94
    ieth
    0.81
    ness
    0.78
     oun
    0.78
    ullivan
    0.76
    atisf
    0.74
    inarily
    0.73
    nesses
    0.72
    ymm
    0.72
    Activations Density 0.008%

    No Known Activations