© 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. 24327
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical acknowledgment and remembrance

    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
    0:0.07
    1:0.01
    2:0.14
    3:0.24
    4:0.03
    5:0.09
    6:0.02
    7:0.09
    8:0.04
    9:0.02
    10:0.17
    11:0.04
    Negative Logits
    Assistant
    -2.34
    Ops
    -2.34
    �醒
    -2.30
     stabilization
    -2.30
    Operation
    -2.27
    Instead
    -2.26
    pressure
    -2.23
    >>
    -2.19
    Minimum
    -2.18
    Recommend
    -2.18
    POSITIVE LOGITS
     timeless
    3.89
     revered
    3.78
     folklore
    3.68
     legends
    3.65
     legend
    3.61
     immortal
    3.53
     commemor
    3.51
     vener
    3.48
     centuries
    3.37
     descendants
    3.33
    Activations Density 0.795%

    No Known Activations