© 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. 18023
    Prev
    Next
    INDEX
    Explanations

    mentions of lions and related feline characteristics or sightings

    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
    0:0.06
    1:0.02
    2:0.06
    3:0.04
    4:0.05
    5:0.02
    6:0.29
    7:0.04
    8:0.06
    9:0.23
    10:0.02
    11:0.04
    Negative Logits
     Ichigo
    -3.87
    sbm
    -3.83
    Glass
    -3.41
     Eps
    -3.32
    esthes
    -3.32
    SpaceEngineers
    -3.30
    ENTS
    -3.29
     Substance
    -3.29
     AST
    -3.29
     Bleach
    -3.25
    POSITIVE LOGITS
     Lion
    10.53
     Lions
    9.40
     lions
    8.08
     lion
    7.96
     Leopard
    4.92
     Liv
    4.89
     carniv
    4.64
     Panther
    4.54
     Wolves
    4.42
     wolf
    4.42
    Activations Density 0.006%

    No Known Activations