© 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. 10-ATT-KK
    11. 8566
    Prev
    Next
    INDEX
    Explanations

    statistical data related to baseball performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.13
    1:0.04
    2:0.06
    3:0.06
    4:0.11
    5:0.02
    6:0.05
    7:0.16
    8:0.05
    9:0.06
    10:0.11
    11:0.09
    Negative Logits
     Loki
    -2.44
     Metatron
    -2.34
    nil
    -2.29
     toilets
    -2.22
    phrine
    -2.22
    func
    -2.21
     esports
    -2.18
     gymn
    -2.18
     medic
    -2.15
    pell
    -2.10
    POSITIVE LOGITS
     WH
    3.19
    ERA
    2.94
    ITCH
    2.81
     batters
    2.80
     ERA
    2.69
    HOU
    2.67
     WAR
    2.62
     RIS
    2.61
    WH
    2.61
     BOX
    2.60
    Activations Density 0.016%

    No Known Activations