© 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. 27403
    Prev
    Next
    INDEX
    Explanations

    phrases related to player transfers and contractual changes in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    1:0.01
    2:0.07
    3:0.08
    4:0.10
    5:0.03
    6:0.04
    7:0.17
    8:0.04
    9:0.05
    10:0.15
    11:0.19
    Negative Logits
     Intervention
    -1.34
    ole
    -1.31
    sers
    -1.26
    ctions
    -1.26
    xual
    -1.21
    Its
    -1.19
    hop
    -1.19
    opa
    -1.18
    aid
    -1.17
    ns
    -1.16
    POSITIVE LOGITS
     midway
    1.34
    BuyableInstoreAndOnline
    1.29
    ermanent
    1.21
    �
    1.20
     coincided
    1.18
     unsett
    1.15
    waukee
    1.14
     rupt
    1.13
     overflow
    1.12
    EEK
    1.12
    Activations Density 0.004%

    No Known Activations