© 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. 10788
    Prev
    Next
    INDEX
    Explanations

    parenthetical statements or notations

    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
    0:0.16
    1:0.03
    2:0.03
    3:0.08
    4:0.12
    5:0.13
    6:0.04
    7:0.15
    8:0.08
    9:0.01
    10:0.08
    11:0.03
    Negative Logits
    \":
    -1.99
     GoPro
    -1.97
    puters
    -1.95
     synchronized
    -1.90
     Huntington
    -1.88
    hiba
    -1.84
     Thumbnails
    -1.84
     polyg
    -1.83
     Phot
    -1.82
    oult
    -1.79
    POSITIVE LOGITS
    atis
    2.14
    zb
    2.03
    Db
    2.02
    aband
    1.90
     QUEST
    1.87
    jit
    1.85
     MLA
    1.84
     Sz
    1.83
    avia
    1.81
    isch
    1.81
    Activations Density 0.000%

    No Known Activations