© 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. 9-ATT-KK
    11. 5399
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with professional organizations and their fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.05
    3:0.50
    4:0.02
    5:0.09
    6:0.02
    7:0.05
    8:0.04
    9:0.02
    10:0.05
    11:0.02
    Negative Logits
     trickle
    -2.33
     paradise
    -2.24
     exodus
    -2.24
     outage
    -2.23
     update
    -2.21
     snowball
    -2.21
     timeline
    -2.20
     reboot
    -2.16
     backdoor
    -2.15
     outp
    -2.13
    POSITIVE LOGITS
     Colleges
    2.63
     Profession
    2.58
     Officers
    2.41
     Females
    2.41
     Occupations
    2.41
     Universities
    2.38
     Inspect
    2.34
     Conduct
    2.32
     Lawyers
    2.28
     Literature
    2.27
    Activations Density 0.269%

    No Known Activations