© 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. 33325
    Prev
    Next
    INDEX
    Explanations

    personal experiences and emotions related to self-defense and interpersonal conflict

    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
    0:0.03
    1:0.02
    2:0.03
    3:0.05
    4:0.02
    5:0.09
    6:0.03
    7:0.02
    8:0.06
    9:0.12
    10:0.40
    11:0.07
    Negative Logits
     Canaver
    -2.27
     Akin
    -1.90
    onential
    -1.84
    odder
    -1.82
     algorith
    -1.79
    ween
    -1.76
    zees
    -1.73
    isite
    -1.65
    omsday
    -1.64
     predicting
    -1.62
    POSITIVE LOGITS
     Leilan
    2.35
    ────
    2.14
    ulk
    2.12
    龍喚士
    1.99
     vanity
    1.88
     protested
    1.85
     resists
    1.83
    priv
    1.80
     endured
    1.76
    raught
    1.74
    Activations Density 0.332%

    No Known Activations