© 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. 15286
    Prev
    Next
    INDEX
    Explanations

    sports-related achievements and records

    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
    0:0.04
    1:0.02
    2:0.05
    3:0.19
    4:0.02
    5:0.07
    6:0.02
    7:0.07
    8:0.04
    9:0.02
    10:0.38
    11:0.02
    Negative Logits
    glers
    -1.93
    uggest
    -1.89
    udeb
    -1.84
     guesses
    -1.82
    better
    -1.80
    might
    -1.78
    opoulos
    -1.76
    hop
    -1.76
     excuses
    -1.76
    little
    -1.75
    POSITIVE LOGITS
     consecut
    2.88
     successfully
    2.50
     EVER
    2.16
     formally
    2.15
     patented
    2.14
     consecutive
    2.13
     simultaneously
    2.08
     publicly
    2.05
     ever
    2.04
     concurrently
    2.02
    Activations Density 0.117%

    No Known Activations