© 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. 12130
    Prev
    Next
    INDEX
    Explanations

    names of locations or specific places, potentially related to transport or infrastructure

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

    mentions of specific locations and associated data

    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
    0:0.03
    1:0.04
    2:0.11
    3:0.14
    4:0.03
    5:0.03
    6:0.21
    7:0.11
    8:0.05
    9:0.06
    10:0.07
    11:0.05
    Negative Logits
    arte
    -1.13
     Expand
    -1.13
    Accessory
    -1.06
     majesty
    -0.99
     redund
    -0.95
     SF
    -0.95
    tein
    -0.92
     hormones
    -0.92
     Martian
    -0.91
     mindfulness
    -0.90
    POSITIVE LOGITS
    ��
    1.24
    apolis
    1.20
    leans
    1.13
    ovych
    1.07
    wire
    1.07
    anders
    1.05
    itol
    1.05
    代
    1.04
    nik
    1.04
    hoff
    1.04
    Activations Density 0.018%

    No Known Activations