© 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. 21541
    Prev
    Next
    INDEX
    Explanations

    elements of structured or organized information, particularly in argumentative or analytical content

    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
    0:0.03
    1:0.04
    2:0.05
    3:0.19
    4:0.07
    5:0.08
    6:0.03
    7:0.10
    8:0.03
    9:0.04
    10:0.28
    11:0.03
    Negative Logits
     happily
    -2.46
     anymore
    -2.42
     pending
    -2.32
     indefinitely
    -2.11
     buzzing
    -2.10
     forever
    -2.08
     awaiting
    -2.01
     ticking
    -2.00
     merry
    -1.99
    ahoo
    -1.97
    POSITIVE LOGITS
    Firstly
    4.36
     Firstly
    4.33
    First
    3.99
     First
    3.35
    first
    3.09
     first
    2.82
     Initially
    2.78
     Specifically
    2.63
    ¶
    2.32
     FIRST
    2.32
    Activations Density 0.171%

    No Known Activations