© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 9594
    Prev
    Next
    INDEX
    Explanations

    terms related to competition and ranking within a creative or performance context

    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
    0:0.05
    1:0.02
    2:0.05
    3:0.23
    4:0.02
    5:0.07
    6:0.02
    7:0.04
    8:0.02
    9:0.02
    10:0.39
    11:0.01
    Negative Logits
    return
    -2.27
    submit
    -1.93
     collisions
    -1.93
     aborted
    -1.82
     abort
    -1.78
    iling
    -1.77
     reinvest
    -1.76
    incre
    -1.76
    enth
    -1.75
     protested
    -1.75
    POSITIVE LOGITS
     stereotype
    2.69
     nicely
    2.68
     neatly
    2.58
     trope
    2.42
     description
    2.39
     seamlessly
    2.35
     snug
    2.31
     stereotypes
    2.27
     comfortably
    2.20
     criteria
    2.18
    Activations Density 0.106%

    No Known Activations