© 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. 686
    Prev
    Next
    INDEX
    Explanations

    repetitive conjunctions and phrases that convey continuity or connection in a narrative

    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
    1:0.24
    2:0.05
    3:0.16
    4:0.03
    5:0.07
    6:0.02
    7:0.15
    8:0.04
    9:0.03
    10:0.06
    11:0.06
    Negative Logits
    ],[
    -2.41
    .?
    -2.41
    approximately
    -2.40
    DL
    -2.33
    Due
    -2.27
    LY
    -2.21
    [/
    -2.13
     Depending
    -2.09
     Unlike
    -2.06
     Prel
    -2.05
    POSITIVE LOGITS
     levers
    2.51
    ��
    2.30
    antry
    2.26
    packing
    2.21
     plotting
    2.20
    osaurus
    2.16
     scaff
    2.13
     awa
    2.12
    gage
    2.11
    omics
    2.09
    Activations Density 0.001%

    No Known Activations