© 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. 38246
    Prev
    Next
    INDEX
    Explanations

    instances of the word "it" and references to forgetting or neglecting

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.02
    1:0.02
    2:0.10
    3:0.08
    4:0.25
    5:0.02
    6:0.05
    7:0.22
    8:0.04
    9:0.04
    10:0.04
    11:0.06
    Negative Logits
    affected
    -1.50
    elled
    -1.46
    itely
    -1.42
    agate
    -1.37
    fired
    -1.36
    latable
    -1.36
    rieved
    -1.35
    oplan
    -1.35
     Architects
    -1.34
     respectively
    -1.33
    POSITIVE LOGITS
     behavi
    1.59
     pesky
    1.58
    Anyway
    1.57
     specificity
    1.56
     altogether
    1.54
    esson
    1.49
     hemor
    1.48
     anten
    1.46
     distinctions
    1.44
     caveats
    1.44
    Activations Density 0.001%

    No Known Activations