© 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. 22362
    Prev
    Next
    INDEX
    Explanations

    connections to concepts related to creation, collaboration, and proof

    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
    1:0.10
    2:0.06
    3:0.05
    4:0.02
    5:0.05
    6:0.15
    7:0.03
    8:0.03
    9:0.31
    10:0.03
    11:0.04
    Negative Logits
    WM
    -3.77
     Saunders
    -3.75
    emo
    -3.53
     animate
    -3.47
     Swan
    -3.41
     nep
    -3.39
    wm
    -3.35
     Schwar
    -3.32
    NE
    -3.24
    uchin
    -3.23
    POSITIVE LOGITS
     Proof
    6.87
    Proof
    6.22
     proof
    6.15
     proofs
    5.84
    proof
    5.60
     Boll
    4.18
     prove
    4.00
     proving
    3.90
     attest
    3.73
     proven
    3.45
    Activations Density 0.001%

    No Known Activations