© 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. 17659
    Prev
    Next
    INDEX
    Explanations

    events related to significant incidents or occurrences

    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
    1:0.09
    2:0.03
    3:0.05
    4:0.06
    5:0.04
    6:0.06
    7:0.03
    8:0.02
    9:0.42
    10:0.06
    11:0.05
    Negative Logits
    773
    -3.23
     Cao
    -3.21
    763
    -3.10
    �
    -3.09
    userc
    -3.05
     CAP
    -2.95
    uders
    -2.94
    783
    -2.92
    Cu
    -2.89
     Haku
    -2.89
    POSITIVE LOGITS
     Sunday
    5.93
    Sunday
    5.80
     Sundays
    4.75
    yss
    3.43
     Samar
    3.26
    dyl
    3.25
     Benny
    3.16
    TY
    3.13
     490
    3.08
     Meteor
    3.04
    Activations Density 0.025%

    No Known Activations