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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 11868
    Prev
    Next
    INDEX
    Explanations

    references to the reader in a direct and personal manner

    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
    0:0.19
    1:0.03
    2:0.06
    3:0.16
    4:0.10
    5:0.05
    6:0.04
    7:0.06
    8:0.08
    9:0.03
    10:0.13
    11:0.04
    Negative Logits
     targ
    -2.43
    tackle
    -2.42
     negotiators
    -2.34
     replay
    -2.33
     jury
    -2.23
     pawn
    -2.21
     incompet
    -2.20
     tact
    -2.17
     jurors
    -2.15
     garn
    -2.13
    POSITIVE LOGITS
     cannabin
    2.48
     Spiegel
    2.45
     Jerusalem
    2.37
     Advent
    2.35
    Reader
    2.31
    nw
    2.29
    ミ
    2.21
    DragonMagazine
    2.21
    ructose
    2.19
     Gutenberg
    2.18
    Activations Density 0.001%

    No Known Activations