© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 19338
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions that indicate connections between ideas

    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
    0:0.09
    1:0.02
    2:0.04
    3:0.04
    4:0.06
    5:0.03
    6:0.22
    7:0.07
    8:0.16
    9:0.16
    10:0.03
    11:0.04
    Negative Logits
     Amit
    -3.64
     athe
    -3.52
     dairy
    -3.51
    ikk
    -3.48
    tml
    -3.44
     Brah
    -3.40
     KP
    -3.39
     Vand
    -3.38
    heed
    -3.38
     Pradesh
    -3.33
    POSITIVE LOGITS
     Raven
    10.98
    Raven
    10.70
     Ravens
    7.29
     raven
    6.06
     Emerald
    4.36
    Baltimore
    4.30
     Cran
    4.13
     Owl
    4.06
    oenix
    4.02
     Torch
    4.02
    Activations Density 0.001%

    No Known Activations