© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43901
    Prev
    Next
    INDEX
    Explanations

    references to competitive rankings or league standings related to sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.04
    2:0.05
    3:0.06
    4:0.05
    5:0.04
    6:0.42
    7:0.04
    8:0.05
    9:0.06
    10:0.07
    11:0.05
    Negative Logits
    FTWARE
    -1.34
     stringent
    -1.29
     doorstep
    -1.27
     dedicate
    -1.25
     compulsion
    -1.22
     exact
    -1.22
     mantle
    -1.22
     hesitation
    -1.20
     margins
    -1.17
    ensical
    -1.16
    POSITIVE LOGITS
    reau
    1.56
    grain
    1.36
    eland
    1.33
    orno
    1.31
    ierrez
    1.30
    espie
    1.30
     Compass
    1.27
    ér
    1.25
    anos
    1.21
    plot
    1.21
    Activations Density 0.054%

    No Known Activations