© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 28260
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that emphasize a relation or difference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.03
    2:0.13
    3:0.06
    4:0.08
    5:0.04
    6:0.08
    7:0.18
    8:0.09
    9:0.04
    10:0.07
    11:0.11
    Negative Logits
     guiActive
    -1.87
     bye
    -1.80
     match
    -1.59
     mimic
    -1.57
     unbeat
    -1.56
     rematch
    -1.55
     allegiance
    -1.49
    bye
    -1.48
     farewell
    -1.47
     goodbye
    -1.46
    POSITIVE LOGITS
    population
    2.31
    levels
    1.72
    Area
    1.72
    HUD
    1.72
    mental
    1.67
    conom
    1.64
    STEM
    1.64
    projects
    1.63
    urgical
    1.62
    Corp
    1.62
    Activations Density 0.000%

    No Known Activations