© 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. 8721
    Prev
    Next
    INDEX
    Explanations

    questions, particularly those seeking information or clarification

    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
    0:0.16
    1:0.08
    2:0.08
    3:0.05
    4:0.03
    5:0.07
    6:0.02
    7:0.04
    8:0.20
    9:0.07
    10:0.05
    11:0.10
    Negative Logits
    theless
    -1.73
    rans
    -1.71
    sole
    -1.61
    rontal
    -1.53
    pard
    -1.52
    nen
    -1.51
    carb
    -1.51
    channel
    -1.49
    aroo
    -1.47
    pes
    -1.47
    POSITIVE LOGITS
     Lastly
    2.05
     Logged
    1.87
     Credits
    1.80
     Guides
    1.75
     Trails
    1.74
     Achievements
    1.72
     Finally
    1.69
     Et
    1.66
     Thief
    1.64
     Tactics
    1.59
    Activations Density 0.010%

    No Known Activations