© 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. 4135
    Prev
    Next
    INDEX
    Explanations

    references to specific places, events, or occurrences

    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
    0:0.13
    1:0.37
    2:0.03
    3:0.03
    4:0.02
    5:0.17
    6:0.03
    7:0.02
    8:0.06
    9:0.03
    10:0.03
    11:0.02
    Negative Logits
    rica
    -2.09
    sonian
    -1.88
    edia
    -1.88
     marsh
    -1.88
    arian
    -1.83
    URA
    -1.82
    ć
    -1.81
     galactic
    -1.80
     caravan
    -1.80
     cal
    -1.79
    POSITIVE LOGITS
     Extensions
    2.59
     Behind
    2.56
     Corruption
    2.54
     Where
    2.45
     Outs
    2.44
     Beyond
    2.41
    Exit
    2.40
     Within
    2.39
     Impossible
    2.38
     Over
    2.37
    Activations Density 0.102%

    No Known Activations