© 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. 6664
    Prev
    Next
    INDEX
    Explanations

    expressions related to existential concepts and human 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
    0:0.02
    1:0.02
    2:0.03
    3:0.09
    4:0.03
    5:0.43
    6:0.04
    7:0.05
    8:0.04
    9:0.01
    10:0.11
    11:0.09
    Negative Logits
     corrid
    -3.69
    DragonMagazine
    -3.60
     mosqu
    -3.47
    ModLoader
    -3.34
    GBT
    -3.27
     defic
    -3.20
    avorite
    -3.18
    Magikarp
    -3.18
    ワン
    -3.11
    inventoryQuantity
    -3.04
    POSITIVE LOGITS
    ,
    3.71
     and
    3.39
    —
    3.32
    *,
    3.30
    ;
    3.20
    .
    3.14
     though
    3.03
     –
    3.02
     (
    3.00
     --
    2.99
    Activations Density 1.549%

    No Known Activations