© 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. 10-ATT-KK
    11. 10810
    Prev
    Next
    INDEX
    Explanations

    phrases related to violence and personal loss

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.22
    1:0.06
    2:0.08
    3:0.04
    4:0.03
    5:0.03
    6:0.21
    7:0.09
    8:0.03
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
     Sno
    -2.83
     Moz
    -2.76
     innov
    -2.65
     Mellon
    -2.64
     Wolfgang
    -2.59
    brance
    -2.59
     Penguin
    -2.57
     Hamburg
    -2.54
     sniff
    -2.53
     compr
    -2.53
    POSITIVE LOGITS
    Cast
    8.58
     Cast
    8.30
     cast
    7.98
     casting
    7.45
     casts
    7.36
     Casting
    6.94
    cast
    6.65
    casting
    6.20
    CAST
    5.56
    casts
    5.36
    Activations Density 0.025%

    No Known Activations