© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10274
    Prev
    Next
    INDEX
    Explanations

    references to grizzly bears and their behavior

    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
    0:0.14
    1:0.02
    2:0.16
    3:0.07
    4:0.03
    5:0.07
    6:0.09
    7:0.05
    8:0.17
    9:0.10
    10:0.03
    11:0.02
    Negative Logits
     Jinn
    -3.58
    ��極
    -3.17
     Grenade
    -3.09
    ento
    -2.97
     Gaal
    -2.96
     Bacon
    -2.94
     Nether
    -2.93
    Manchester
    -2.92
     Herrera
    -2.92
     java
    -2.90
    POSITIVE LOGITS
     polar
    6.11
     Polar
    5.76
     bears
    5.37
     Arctic
    4.81
     grizz
    4.68
     bear
    4.65
     Grizz
    4.33
     Siberian
    4.18
    Bear
    4.08
     Bear
    4.01
    Activations Density 0.009%

    No Known Activations