© 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. 44016
    Prev
    Next
    INDEX
    Explanations

    punctuated phrases indicating events or actions

    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
    0:0.01
    1:0.01
    2:0.15
    3:0.10
    4:0.12
    5:0.04
    6:0.03
    7:0.14
    8:0.10
    9:0.03
    10:0.08
    11:0.13
    Negative Logits
    �士
    -1.45
     Guinness
    -1.38
    ortment
    -1.38
    viation
    -1.35
     Ambro
    -1.34
     Gul
    -1.31
    ��
    -1.31
     Founding
    -1.28
    ワン
    -1.26
     Malt
    -1.26
    POSITIVE LOGITS
    uberty
    1.47
     horizon
    1.39
     ])
    1.36
     wont
    1.32
    ])
    1.25
    ENGTH
    1.22
     })
    1.20
    insert
    1.19
    ework
    1.17
     ))
    1.16
    Activations Density 0.026%

    No Known Activations