© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8590
    Prev
    Next
    INDEX
    Explanations

    punctuated endings and their significance in storytelling

    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
    2:0.06
    3:0.04
    4:0.05
    5:0.04
    6:0.26
    7:0.07
    8:0.10
    9:0.16
    10:0.03
    11:0.03
    Negative Logits
    UFF
    -3.94
     Droid
    -3.55
     Hemp
    -3.53
    NN
    -3.51
     Miz
    -3.46
     Jets
    -3.46
    iants
    -3.44
     hemp
    -3.43
    Raid
    -3.37
     Robbie
    -3.36
    POSITIVE LOGITS
     Chal
    10.30
     Cha
    6.31
    chal
    4.38
     chapel
    4.12
     Chamberlain
    3.98
     cha
    3.97
     Chaos
    3.68
    scl
    3.59
     Chapel
    3.59
     Chou
    3.58
    Activations Density 0.002%

    No Known Activations