© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 3496
    Prev
    Next
    INDEX
    Explanations

    expressions related to physical fitness and recovery from injury

    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
    0:0.05
    1:0.02
    2:0.16
    3:0.20
    4:0.03
    5:0.16
    6:0.03
    7:0.08
    8:0.05
    9:0.02
    10:0.11
    11:0.03
    Negative Logits
    uphem
    -2.07
    ulhu
    -2.05
    onymous
    -2.02
     Defendants
    -1.97
    ueless
    -1.95
    ominated
    -1.92
    advertising
    -1.81
    stakes
    -1.79
    UCT
    -1.79
     fictitious
    -1.78
    POSITIVE LOGITS
     muscles
    3.09
     stamina
    3.00
     workouts
    2.92
     muscle
    2.77
     endurance
    2.76
     aerobic
    2.72
     fatigue
    2.69
     stiffness
    2.60
     recovery
    2.54
     workout
    2.52
    Activations Density 0.584%

    No Known Activations