© 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. 4914
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the establishment or implementation of systems, strategies, or regulations

    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
    2:0.29
    3:0.05
    4:0.19
    5:0.02
    6:0.08
    7:0.11
    8:0.05
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
    renheit
    -1.74
    pleted
    -1.64
    facing
    -1.62
    hya
    -1.59
     Somew
    -1.55
    telling
    -1.54
    urger
    -1.53
    leground
    -1.49
    vana
    -1.46
    lege
    -1.46
    POSITIVE LOGITS
     policies
    1.50
     foundations
    1.50
     impunity
    1.48
     restraints
    1.45
     precedent
    1.43
     safeguards
    1.42
     profiles
    1.42
     groundwork
    1.42
     plans
    1.41
     warranties
    1.41
    Activations Density 0.002%

    No Known Activations