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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22050
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations related to organizations and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.02
    2:0.12
    3:0.09
    4:0.05
    5:0.11
    6:0.04
    7:0.04
    8:0.08
    9:0.13
    10:0.13
    11:0.04
    Negative Logits
     adversity
    -1.20
    Increase
    -1.14
    =-=-=-=-
    -1.08
     strangers
    -1.03
     majesty
    -1.02
     Stranger
    -1.01
     guiName
    -0.99
    eryl
    -0.98
     mov
    -0.97
     gimm
    -0.95
    POSITIVE LOGITS
    ):
    1.47
    )—
    1.46
    emale
    1.43
    ),
    1.35
    +)
    1.32
    UGC
    1.30
    )--
    1.25
    ).[
    1.24
    )
    1.23
    sonian
    1.21
    Activations Density 0.084%

    No Known Activations