© 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. 10-ATT-KK
    11. 12774
    Prev
    Next
    INDEX
    Explanations

    references to geographical directions and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.16
    2:0.05
    3:0.30
    4:0.05
    5:0.02
    6:0.03
    7:0.12
    8:0.04
    9:0.04
    10:0.04
    11:0.06
    Negative Logits
    lished
    -2.66
    wire
    -2.48
     Lifetime
    -2.17
    aneous
    -2.15
    OTOS
    -2.14
     Stress
    -2.11
     Replay
    -2.06
    mint
    -2.04
     Random
    -2.02
    Myth
    -2.00
    POSITIVE LOGITS
     west
    7.38
     east
    7.18
     south
    7.09
     north
    6.80
     northeast
    6.21
     southeast
    6.19
     northwest
    6.13
     southwest
    6.09
    east
    5.53
    south
    5.50
    Activations Density 0.145%

    No Known Activations