© 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. 10-ATT-KK
    11. 14493
    Prev
    Next
    INDEX
    Explanations

    connections and relationships within social contexts

    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
    0:0.02
    1:0.02
    2:0.02
    3:0.03
    4:0.11
    5:0.02
    6:0.02
    7:0.46
    8:0.02
    9:0.05
    10:0.01
    11:0.17
    Negative Logits
    stocks
    -3.14
    Login
    -2.94
    Kate
    -2.83
    Facebook
    -2.81
     PRESIDENT
    -2.65
    Beck
    -2.50
    Brand
    -2.45
    Hart
    -2.44
     Hart
    -2.41
    Artist
    -2.34
    POSITIVE LOGITS
     Crab
    2.83
     Nile
    2.76
    imum
    2.71
     Slay
    2.69
     Vive
    2.63
     Mae
    2.59
    ──
    2.56
     mummy
    2.53
    cius
    2.37
     Codec
    2.35
    Activations Density 0.036%

    No Known Activations