© 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. 19997
    Prev
    Next
    INDEX
    Explanations

    geographic directions and distances

    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
    0:0.03
    1:0.10
    2:0.04
    3:0.08
    4:0.06
    5:0.05
    6:0.29
    7:0.10
    8:0.03
    9:0.09
    10:0.04
    11:0.04
    Negative Logits
    azo
    -3.58
    Glass
    -3.20
    Gi
    -3.14
    Gam
    -3.12
     Esports
    -3.10
     Glass
    -3.02
     Epstein
    -2.98
     Brut
    -2.94
    Frames
    -2.91
     Blank
    -2.87
    POSITIVE LOGITS
     north
    4.71
    south
    4.54
    heast
    4.49
     south
    4.47
     Southwest
    4.47
     nort
    4.23
     southeast
    4.21
     southwest
    4.21
     east
    4.09
     northwest
    4.07
    Activations Density 0.009%

    No Known Activations