© 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. 27260
    Prev
    Next
    INDEX
    Explanations

    questions and introductory phrases that signal explanations or observations

    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
    0:0.04
    1:0.01
    2:0.07
    3:0.05
    4:0.03
    5:0.11
    6:0.02
    7:0.03
    8:0.41
    9:0.03
    10:0.08
    11:0.05
    Negative Logits
     Kear
    -2.01
    acan
    -1.71
    venge
    -1.70
    prop
    -1.66
    yg
    -1.62
    yp
    -1.58
    wra
    -1.54
    aer
    -1.50
    bec
    -1.46
    arthed
    -1.42
    POSITIVE LOGITS
    ALSE
    1.90
    ulla
    1.87
    ModLoader
    1.79
    soDeliveryDate
    1.67
    earances
    1.61
     affirmative
    1.61
    nexus
    1.60
    microsoft
    1.59
    IDA
    1.54
    odka
    1.54
    Activations Density 0.073%

    No Known Activations