© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 4868
    Prev
    Next
    INDEX
    Explanations

    personality traits and behaviors associated with narcissism

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    phrases and words depicting entitlement and arrogance in behavior

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    uberty
    -0.84
    lain
    -0.81
    merga
    -0.79
    olitan
    -0.75
    anish
    -0.74
     Formation
    -0.74
    aea
    -0.73
    OSH
    -0.71
     Merge
    -0.70
    ledged
    -0.70
    POSITIVE LOGITS
     counterproductive
    1.23
     unethical
    1.22
     immoral
    1.17
     discriminatory
    1.14
     incompetent
    1.14
     explo
    1.13
     impractical
    1.13
     irresponsible
    1.13
     abusive
    1.11
     ineffective
    1.11
    Activations Density 0.179%

    No Known Activations