© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11298
    Prev
    Next
    INDEX
    Explanations

    references to authority and expertise

    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
    0:0.02
    1:0.05
    2:0.16
    3:0.05
    4:0.02
    5:0.07
    6:0.12
    7:0.12
    8:0.11
    9:0.10
    10:0.08
    11:0.05
    Negative Logits
     guiActiveUnfocused
    -1.40
    VERTISEMENT
    -1.38
    their
    -1.30
    ADVERTISEMENT
    -1.26
    rush
    -1.23
     assumptions
    -1.21
    Were
    -1.19
    ppings
    -1.19
    notations
    -1.17
     ensued
    -1.15
    POSITIVE LOGITS
     himself
    1.25
     proud
    1.23
     herself
    1.22
     happiest
    1.22
     diabetic
    1.20
    �
    1.19
    ozyg
    1.15
    aughty
    1.15
    uba
    1.15
     isEnabled
    1.14
    Activations Density 0.069%

    No Known Activations