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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 20566
    Prev
    Next
    INDEX
    Explanations

    mentions of legal processes and actions, particularly related to arrests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.06
    3:0.03
    4:0.06
    5:0.03
    6:0.23
    7:0.06
    8:0.10
    9:0.21
    10:0.03
    11:0.04
    Negative Logits
     Halls
    -3.80
     hall
    -3.69
    Hall
    -3.59
     Hall
    -3.58
    ikh
    -3.57
    Cow
    -3.47
     Kell
    -3.43
     charism
    -3.39
    FM
    -3.34
     Lawn
    -3.30
    POSITIVE LOGITS
     Torres
    11.76
    Tor
    7.13
     TOR
    4.80
     Tor
    4.69
     Toro
    4.65
     Ramos
    4.28
     Timbers
    4.07
     Suarez
    3.85
     Perez
    3.82
     Mata
    3.79
    Activations Density 0.002%

    No Known Activations