© 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. 27779
    Prev
    Next
    INDEX
    Explanations

    references to historical events and their context

    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
    1:0.44
    2:0.02
    3:0.02
    4:0.02
    5:0.15
    6:0.01
    7:0.02
    8:0.04
    9:0.06
    10:0.02
    11:0.02
    Negative Logits
    folder
    -1.94
    thinkable
    -1.94
    dropping
    -1.93
    ovember
    -1.82
    edged
    -1.81
    advertising
    -1.79
    munition
    -1.78
    wash
    -1.75
    pmwiki
    -1.74
    pl
    -1.73
    POSITIVE LOGITS
     Monte
    2.53
     Eur
    2.49
     Kirin
    2.41
     Kin
    2.32
     Lank
    2.26
     Tri
    2.26
     Kenn
    2.22
     Chao
    2.20
     Mn
    2.20
     Hag
    2.19
    Activations Density 0.961%

    No Known Activations