© 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. 6752
    Prev
    Next
    INDEX
    Explanations

    negative emotions or sentiments expressed in the text

    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
    0:0.04
    1:0.05
    2:0.04
    3:0.05
    4:0.05
    5:0.05
    6:0.05
    7:0.06
    8:0.06
    9:0.31
    10:0.04
    11:0.13
    Negative Logits
     myself
    -2.44
     yourself
    -2.31
     inhab
    -2.27
     sounding
    -2.21
     perpetrators
    -2.09
     gener
    -2.04
     deserving
    -2.02
     into
    -2.00
     villains
    -1.98
     acron
    -1.97
    POSITIVE LOGITS
    isites
    2.88
    Patch
    2.69
    Upgrade
    2.68
    rued
    2.63
    patch
    2.30
    isite
    2.27
    stice
    2.27
    icipated
    2.25
    ritten
    2.20
    ascript
    2.18
    Activations Density 0.016%

    No Known Activations