© 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. 3-RES-JB
    11. 16909
    Prev
    Next
    INDEX
    Explanations

    words related to physical appearance and charm

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical attractiveness and charisma

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.83
    imester
    -0.83
    REL
    -0.74
    VK
    -0.69
    uc
    -0.68
    FER
    -0.65
    forums
    -0.65
    alg
    -0.65
     Airl
    -0.65
    uther
    -0.64
    POSITIVE LOGITS
    ly
    1.41
     handsome
    0.93
    glers
    0.88
    liest
    0.88
     prince
    0.86
     citiz
    0.84
    lier
    0.84
     marqu
    0.79
     thous
    0.77
     fellows
    0.77
    Activations Density 0.013%

    No Known Activations