© 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. 10-ATT-KK
    11. 8606
    Prev
    Next
    INDEX
    Explanations

    specific terms related to geographical locations and their attributes

    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
    0:0.04
    1:0.04
    2:0.06
    3:0.08
    4:0.07
    5:0.07
    6:0.03
    7:0.06
    8:0.02
    9:0.32
    10:0.04
    11:0.09
    Negative Logits
     exagger
    -2.50
     attribut
    -2.49
     inaccur
    -2.35
    �
    -2.27
     motivation
    -2.27
     quote
    -2.25
     respons
    -2.22
     behavior
    -2.21
     based
    -2.21
     negatively
    -2.21
    POSITIVE LOGITS
    ��
    3.26
    lands
    3.05
    veyard
    3.01
    insula
    2.87
    ropolis
    2.86
     desolate
    2.84
    opolis
    2.84
    waters
    2.80
    ranean
    2.77
     wilderness
    2.73
    Activations Density 0.778%

    No Known Activations