Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3160
    Prev
    Next
    INDEX
    Explanations

    discourse markers and references that indicate relationships or 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
    0:0.07
    1:0.03
    2:0.05
    3:0.03
    4:0.07
    5:0.03
    6:0.23
    7:0.05
    8:0.06
    9:0.25
    10:0.03
    11:0.04
    Negative Logits
    ovo
    -4.24
     Gladiator
    -4.09
    ████
    -4.01
    eva
    -3.85
     Chess
    -3.79
    ████████
    -3.64
    achi
    -3.62
     Zh
    -3.59
    arius
    -3.56
    ██
    -3.55
    POSITIVE LOGITS
     Mul
    11.10
     mul
    7.93
     Mulcair
    6.40
     Cul
    4.98
     Cull
    4.90
     Dul
    4.62
     UL
    4.62
     Kil
    4.59
     Poc
    4.56
     Mull
    4.48
    Activations Density 0.007%

    No Known Activations