© 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. 5427
    Prev
    Next
    INDEX
    Explanations

    references to downward movement or actions

    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
    0:0.08
    1:0.07
    2:0.08
    3:0.08
    4:0.08
    5:0.08
    6:0.07
    7:0.08
    8:0.08
    9:0.07
    10:0.09
    11:0.09
    Negative Logits
     dstg
    -3.68
    jri
    -3.16
    UFC
    -3.14
    catentry
    -3.13
    Sac
    -3.03
    odan
    -3.02
     Kobe
    -2.99
    asar
    -2.98
    zona
    -2.97
    CPU
    -2.94
    POSITIVE LOGITS
     Materials
    3.04
     procedural
    2.99
     Applic
    2.99
    .—
    2.96
     Applications
    2.89
     READ
    2.80
     RELE
    2.71
     Amendments
    2.68
     Synt
    2.68
     Delay
    2.66
    Activations Density 0.000%

    No Known Activations