© 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. 17431
    Prev
    Next
    INDEX
    Explanations

    personal expressions of emotional struggles or experiences

    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
    0:0.05
    1:0.05
    2:0.05
    3:0.04
    4:0.06
    5:0.29
    6:0.03
    7:0.04
    8:0.03
    9:0.25
    10:0.03
    11:0.04
    Negative Logits
     advances
    -2.46
     emerges
    -2.27
     proceeds
    -2.25
     binds
    -2.20
    ues
    -2.18
     fades
    -2.15
     destroys
    -2.15
    sworth
    -2.10
     completes
    -2.09
     compounds
    -2.08
    POSITIVE LOGITS
     myself
    3.07
     believe
    2.66
     envision
    2.64
    ________________
    2.47
     recommend
    2.45
     think
    2.45
     envy
    2.42
    �
    2.42
    ÃÂ
    2.42
    ️
    2.41
    Activations Density 0.623%

    No Known Activations