© 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. 16427
    Prev
    Next
    INDEX
    Explanations

    references to rankings and statistics related to athletes or teams

    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
    1:0.16
    2:0.06
    3:0.09
    4:0.08
    5:0.10
    6:0.13
    7:0.04
    8:0.03
    9:0.03
    10:0.02
    11:0.17
    Negative Logits
    asking
    -2.42
     FG
    -2.29
     ether
    -2.26
     KH
    -2.19
     IST
    -2.18
    Commission
    -2.12
    imentary
    -2.10
    Agent
    -2.04
     UDP
    -2.03
    luster
    -2.02
    POSITIVE LOGITS
     No
    4.02
     Nos
    3.52
    No
    2.79
     ninth
    2.72
     Yes
    2.64
     eighth
    2.51
     seventh
    2.35
     sixth
    2.30
     Quart
    2.28
     Morton
    2.27
    Activations Density 0.007%

    No Known Activations