© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15911
    Prev
    Next
    INDEX
    Explanations

    references to Brazilian fans and their emotions, particularly in relation to mourning or significant events in sports

    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
    0:0.12
    1:0.06
    2:0.04
    3:0.08
    4:0.09
    5:0.03
    6:0.19
    7:0.10
    8:0.03
    9:0.06
    10:0.03
    11:0.11
    Negative Logits
    Task
    -3.43
     Task
    -2.85
    覚醒
    -2.81
     srfAttach
    -2.75
    inventoryQuantity
    -2.60
    Prosecut
    -2.58
    Rect
    -2.55
    Serv
    -2.51
    rend
    -2.38
    使
    -2.37
    POSITIVE LOGITS
     fans
    6.61
    Fans
    6.58
     Fans
    6.44
     fan
    5.94
     fandom
    5.64
     fanbase
    5.53
     Fan
    5.45
    Fan
    5.39
    fan
    5.12
     stadium
    4.78
    Activations Density 0.167%

    No Known Activations