© 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. 18907
    Prev
    Next
    INDEX
    Explanations

    phrases indicating current context and circumstances

    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
    0:0.03
    1:0.02
    2:0.07
    3:0.18
    4:0.09
    5:0.09
    6:0.06
    7:0.05
    8:0.05
    9:0.14
    10:0.11
    11:0.05
    Negative Logits
    ogether
    -1.49
    ONSORED
    -1.45
    anwhile
    -1.36
     accordingly
    -1.25
    ————————
    -1.20
     vou
    -1.16
    .�
    -1.13
     srfAttach
    -1.12
    ————
    -1.09
    vertisements
    -1.06
    POSITIVE LOGITS
    initialized
    1.22
    enum
    1.14
    ictionary
    1.11
     embodiments
    1.11
    shall
    1.09
     genomic
    1.04
    Congress
    1.03
     Gamergate
    1.02
     Wiki
    1.01
     ][
    1.01
    Activations Density 0.376%

    No Known Activations