© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 16767
    Prev
    Next
    INDEX
    Explanations

    discussions about health-related risks and comparisons of treatment efficacy

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.07
    1:0.04
    2:0.08
    3:0.18
    4:0.09
    5:0.09
    6:0.05
    7:0.07
    8:0.07
    9:0.08
    10:0.06
    11:0.06
    Negative Logits
    ratulations
    -1.69
     manifest
    -1.66
     conceivable
    -1.65
     fingerprints
    -1.63
     satell
    -1.55
    abol
    -1.54
     Carnage
    -1.53
     sucked
    -1.52
    ...]
    -1.51
     amongst
    -1.47
    POSITIVE LOGITS
    lier
    1.99
    arger
    1.92
    quickShipAvailable
    1.88
    illac
    1.82
    posure
    1.79
    oys
    1.75
     Paste
    1.73
    eca
    1.71
    amins
    1.70
    ••
    1.67
    Activations Density 0.002%

    No Known Activations