© 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. 419
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and specific function words

    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
    0:0.06
    1:0.04
    2:0.06
    3:0.04
    4:0.06
    5:0.05
    6:0.19
    7:0.05
    8:0.08
    9:0.25
    10:0.03
    11:0.04
    Negative Logits
     Hawai
    -4.26
    packing
    -3.95
    aho
    -3.75
    �
    -3.58
     Hawaiian
    -3.56
    pack
    -3.48
     Pilgrim
    -3.38
    hun
    -3.36
    uo
    -3.33
    packs
    -3.32
    POSITIVE LOGITS
     Der
    9.63
    Der
    9.24
     Derby
    8.40
    der
    6.40
     der
    5.85
    DER
    5.08
     Dahl
    5.01
     Dixon
    4.78
     Die
    4.73
    Die
    4.65
    Activations Density 0.003%

    No Known Activations