© 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. 3-ATT-KK
    11. 5823
    Prev
    Next
    INDEX
    Explanations

    comparative and superlative adjectives or phrases indicating improvement or decline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.03
    2:0.05
    3:0.05
    4:0.02
    5:0.45
    6:0.06
    7:0.05
    8:0.06
    9:0.03
    10:0.08
    11:0.05
    Negative Logits
    agent
    -1.93
    andise
    -1.90
    submit
    -1.82
    agents
    -1.80
    asta
    -1.73
    brance
    -1.69
    authorized
    -1.68
     swearing
    -1.68
    andestine
    -1.67
    intent
    -1.67
    POSITIVE LOGITS
    izons
    2.24
    inventoryQuantity
    2.21
     decreases
    1.98
     increases
    1.97
    efficiency
    1.90
     vitamins
    1.87
     decrease
    1.83
     reductions
    1.82
     absorb
    1.79
     gains
    1.77
    Activations Density 0.201%

    No Known Activations