© 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. 43559
    Prev
    Next
    INDEX
    Explanations

    terms related to legal entities and formal structures, particularly in a corporate or governmental context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.05
    1:0.03
    2:0.48
    3:0.05
    4:0.05
    5:0.03
    6:0.05
    7:0.04
    8:0.04
    9:0.04
    10:0.06
    11:0.04
    Negative Logits
    htaking
    -1.99
    emouth
    -1.82
    inventoryQuantity
    -1.64
     ripe
    -1.62
    covered
    -1.55
    AppData
    -1.54
    Ranked
    -1.53
    imgur
    -1.51
    quartered
    -1.50
    natureconservancy
    -1.49
    POSITIVE LOGITS
    tein
    1.92
     vengeance
    1.73
    ctive
    1.72
    ibus
    1.62
     Strauss
    1.56
    aft
    1.50
     Tant
    1.49
    izontal
    1.49
     dh
    1.48
    idad
    1.46
    Activations Density 0.253%

    No Known Activations