© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-ATT-KK
    11. 14195
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal statements and claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.21
    1:0.08
    2:0.09
    3:0.05
    4:0.04
    5:0.04
    6:0.11
    7:0.10
    8:0.01
    9:0.06
    10:0.09
    11:0.05
    Negative Logits
     Akin
    -3.17
     Camel
    -3.15
     Feld
    -3.08
     Ludwig
    -3.00
    Iowa
    -2.99
    ieval
    -2.98
     charism
    -2.91
     IGF
    -2.85
    inburgh
    -2.76
     Citation
    -2.74
    POSITIVE LOGITS
     Torres
    10.50
    Tor
    5.78
     Rivera
    4.08
     Timbers
    3.85
     Lopez
    3.80
     Ramos
    3.80
     Flores
    3.76
     Morales
    3.66
     Toro
    3.63
     Garc
    3.63
    Activations Density 0.003%

    No Known Activations