© 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. 1574
    Prev
    Next
    INDEX
    Explanations

    relationships and implications of actions or events

    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
    0:0.03
    1:0.01
    2:0.18
    3:0.17
    4:0.09
    5:0.03
    6:0.03
    7:0.06
    8:0.08
    9:0.07
    10:0.16
    11:0.04
    Negative Logits
     enthusi
    -1.93
     mosqu
    -1.70
    ADRA
    -1.57
    psey
    -1.56
     conclud
    -1.55
     Bucc
    -1.51
     ultras
    -1.50
     helicop
    -1.49
     Giul
    -1.47
     undermin
    -1.45
    POSITIVE LOGITS
    widget
    1.66
    ˈ
    1.62
     Means
    1.59
    estamp
    1.59
    itars
    1.58
     ·
    1.56
     Released
    1.52
    fml
    1.50
    common
    1.49
    ヘラ
    1.48
    Activations Density 0.006%

    No Known Activations