© 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. 5-ATT-KK
    11. 6850
    Prev
    Next
    INDEX
    Explanations

    monetary values and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.20
    1:0.28
    2:0.04
    3:0.03
    4:0.02
    5:0.14
    6:0.03
    7:0.01
    8:0.08
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
     Ezek
    -2.88
     Zed
    -2.19
     Quin
    -2.09
     Dia
    -2.07
     Ibrahim
    -2.00
     Caleb
    -1.98
     Kahn
    -1.97
     Kell
    -1.92
     Him
    -1.91
     Yor
    -1.91
    POSITIVE LOGITS
    100
    2.91
    300
    2.78
    200
    2.71
    400
    2.58
    150
    2.56
    700
    2.53
    500
    2.49
    800
    2.42
    1000
    2.40
    600
    2.32
    Activations Density 0.012%

    No Known Activations