© 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. 3-ATT-KK
    11. 12515
    Prev
    Next
    INDEX
    Explanations

    words related to specific places or events, especially those with cultural or traditional significance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to places, particularly those associated with saints or notable historical figures

    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
    0:0.04
    1:0.05
    2:0.10
    3:0.20
    4:0.01
    5:0.02
    6:0.13
    7:0.10
    8:0.04
    9:0.06
    10:0.06
    11:0.12
    Negative Logits
    ividual
    -1.31
    geoning
    -1.28
    ahon
    -1.24
     omission
    -1.15
    ibly
    -1.14
    ��
    -1.10
    soDeliveryDate
    -1.10
     variance
    -1.06
    ERG
    -1.05
    SourceFile
    -1.04
    POSITIVE LOGITS
    ê
    1.13
    jong
    1.06
     Vim
    1.06
     Nou
    1.04
    heit
    1.01
     Dign
    1.01
     Mansion
    1.00
     Galile
    0.99
     Pere
    0.99
     Hera
    0.98
    Activations Density 0.009%

    No Known Activations