© 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. 22483
    Prev
    Next
    INDEX
    Explanations

    connections or relationships between phrases and clauses in the text

    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
    0:0.03
    1:0.42
    2:0.05
    3:0.04
    4:0.09
    5:0.05
    6:0.04
    7:0.10
    8:0.03
    9:0.04
    10:0.03
    11:0.04
    Negative Logits
    Usually
    -2.73
    extremely
    -2.58
    buff
    -2.50
    PORT
    -2.46
    emb
    -2.40
    completely
    -2.40
     Dragonbound
    -2.39
    ached
    -2.36
    Sometimes
    -2.33
     Aside
    -2.31
    POSITIVE LOGITS
    those
    6.55
     those
    6.34
    Those
    5.74
     Those
    5.54
     ones
    3.71
     others
    3.05
    20439
    2.99
     originals
    2.94
     newcomers
    2.92
     subset
    2.78
    Activations Density 0.098%

    No Known Activations