© 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. 9-RES-JB
    11. 10307
    Prev
    Next
    INDEX
    Explanations

    words related to creativity and originality

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to originality and creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FY
    -0.71
    çīĪ
    -0.70
     Reported
    -0.70
    ificantly
    -0.69
    USS
    -0.65
     Cosponsors
    -0.64
    recent
    -0.64
    Latest
    -0.64
    ndum
    -0.63
    oday
    -0.63
    POSITIVE LOGITS
     ALWAYS
    0.88
     sometimes
    0.81
     seldom
    0.76
     Happiness
    0.75
     instinctively
    0.74
     always
    0.74
     often
    0.72
     happiness
    0.71
     Sometimes
    0.71
     rarely
    0.70
    Activations Density 1.123%

    No Known Activations