© 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. 1826
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases and references to numerous occurrences or entities

    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
    1:0.43
    2:0.05
    3:0.06
    4:0.04
    5:0.05
    6:0.04
    7:0.10
    8:0.03
    9:0.04
    10:0.05
    11:0.02
    Negative Logits
    izu
    -2.65
    oret
    -2.54
     minus
    -2.43
    kay
    -2.42
    pret
    -2.32
    isin
    -2.31
    entin
    -2.28
     Pret
    -2.28
     Pillar
    -2.23
     eighth
    -2.22
    POSITIVE LOGITS
     many
    6.88
     Many
    6.17
    many
    6.16
    Many
    5.83
     countless
    4.93
     numerous
    4.79
     innumerable
    4.69
     often
    4.03
     multitude
    4.02
     Often
    3.91
    Activations Density 0.118%

    No Known Activations