© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 13230
    Prev
    Next
    INDEX
    Explanations

    verbs indicating possession or capability

    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
    0:0.04
    1:0.04
    2:0.04
    3:0.32
    4:0.02
    5:0.05
    6:0.02
    7:0.04
    8:0.03
    9:0.02
    10:0.30
    11:0.02
    Negative Logits
    catentry
    -2.36
    Documents
    -2.28
    20439
    -2.21
    Times
    -2.16
    Associated
    -2.10
    payment
    -2.08
     incorrectly
    -2.07
     Mehran
    -2.06
    bid
    -2.04
    published
    -2.04
    POSITIVE LOGITS
     anybody
    2.53
     creativity
    2.36
     wonders
    2.36
     really
    2.35
     fun
    2.32
     interesting
    2.30
     thing
    2.24
     crazy
    2.23
     taste
    2.21
     emptiness
    2.14
    Activations Density 0.053%

    No Known Activations