© 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. 5-ATT-KK
    11. 36310
    Prev
    Next
    INDEX
    Explanations

    references to authority and significant decisions or judgments

    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
    0:0.19
    1:0.29
    2:0.02
    3:0.03
    4:0.01
    5:0.20
    6:0.06
    7:0.01
    8:0.06
    9:0.05
    10:0.02
    11:0.01
    Negative Logits
     laun
    -1.70
     █
    -1.70
     GOODMAN
    -1.70
     DRAG
    -1.65
    pload
    -1.63
    ographic
    -1.56
     UFC
    -1.54
     ABE
    -1.51
     domest
    -1.51
    achus
    -1.51
    POSITIVE LOGITS
    It
    2.13
    Issue
    2.02
    Same
    1.91
    Its
    1.90
    Ir
    1.80
    its
    1.80
    omething
    1.80
    it
    1.80
    IT
    1.77
    Yes
    1.75
    Activations Density 0.009%

    No Known Activations