© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 5484
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and authoritative sources

    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
    0:0.06
    1:0.17
    2:0.03
    3:0.04
    4:0.04
    5:0.25
    6:0.03
    7:0.02
    8:0.13
    9:0.06
    10:0.06
    11:0.04
    Negative Logits
     Rudd
    -1.51
     politics
    -1.45
     vice
    -1.42
     mindset
    -1.40
     Lol
    -1.39
     conscience
    -1.39
     Anarchy
    -1.36
     Sharon
    -1.33
     status
    -1.33
     Legislature
    -1.32
    POSITIVE LOGITS
    shows
    1.95
    qs
    1.78
    ixel
    1.77
    anges
    1.75
    hend
    1.73
    ount
    1.72
    ript
    1.67
    iler
    1.67
    aments
    1.67
    Adds
    1.66
    Activations Density 0.002%

    No Known Activations