© 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. 14436
    Prev
    Next
    INDEX
    Explanations

    medical conditions and their symptoms

    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
    0:0.18
    1:0.02
    2:0.02
    3:0.04
    4:0.12
    5:0.04
    6:0.01
    7:0.38
    8:0.02
    9:0.04
    10:0.05
    11:0.03
    Negative Logits
    etooth
    -3.00
    obyl
    -2.72
    ohm
    -2.64
     Fool
    -2.62
     Pound
    -2.58
    thodox
    -2.58
    arettes
    -2.52
    HF
    -2.51
     Finn
    -2.49
    emption
    -2.49
    POSITIVE LOGITS
     cous
    2.92
     sar
    2.82
     Sar
    2.74
     Stones
    2.74
     corps
    2.71
     hier
    2.69
     Nas
    2.63
     Bac
    2.55
     Nar
    2.54
     Sag
    2.54
    Activations Density 0.002%

    No Known Activations