© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 17268
    Prev
    Next
    INDEX
    Explanations

    words related to biomedical topics and medical conditions

    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
    1:0.02
    2:0.03
    3:0.07
    4:0.05
    5:0.05
    6:0.08
    7:0.04
    8:0.03
    9:0.04
    10:0.09
    11:0.41
    Negative Logits
    >"
    -3.05
    /"
    -3.01
    ]=
    -3.00
    ]"
    -2.94
    -"
    -2.86
    !,
    -2.84
    =
    -2.79
    ?),
    -2.73
    bes
    -2.64
    =/
    -2.52
    POSITIVE LOGITS
     •
    10.13
     ‎
    6.72
     */
    6.02
     ►
    6.00
     ■
    5.95
     »
    5.67
     ''
    5.51
    •
    5.43
     ●
    5.31
     �
    5.28
    Activations Density 0.006%

    No Known Activations