© 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. 6617
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries regarding understanding and introspection

    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
    0:0.03
    1:0.04
    2:0.07
    3:0.27
    4:0.03
    5:0.28
    6:0.02
    7:0.06
    8:0.03
    9:0.02
    10:0.08
    11:0.02
    Negative Logits
     probing
    -2.33
    ruciating
    -2.33
    uggest
    -2.30
    erb
    -2.29
     exasper
    -2.25
     Spotlight
    -2.22
     quizz
    -2.21
     ginger
    -2.19
     scathing
    -2.13
     canv
    -2.13
    POSITIVE LOGITS
    why
    2.95
     WHY
    2.86
     why
    2.70
    ?:
    2.62
    Does
    2.59
    Why
    2.58
    )?
    2.50
    Who
    2.46
    what
    2.37
     whether
    2.36
    Activations Density 0.249%

    No Known Activations