© 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. 18390
    Prev
    Next
    INDEX
    Explanations

    sequences of letters or characters that represent specific identifiers or short forms

    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
    0:0.04
    1:0.00
    2:0.02
    3:0.25
    4:0.06
    5:0.17
    6:0.01
    7:0.27
    8:0.01
    9:0.00
    10:0.10
    11:0.01
    Negative Logits
    quartered
    -2.08
     Stro
    -2.04
     Dull
    -2.01
     Lear
    -2.00
     nurs
    -2.00
     trave
    -1.99
     discont
    -1.99
     contamin
    -1.98
     aspiring
    -1.93
     manip
    -1.91
    POSITIVE LOGITS
    UX
    2.93
    ON
    2.72
    Cu
    2.52
    ETA
    2.51
    heon
    2.50
    encer
    2.47
    EMA
    2.42
    IUM
    2.35
    sha
    2.34
    Eva
    2.32
    Activations Density 0.006%

    No Known Activations