© 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. 5-ATT-KK
    11. 34512
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of ongoing actions or current events

    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
    2:0.10
    3:0.16
    4:0.13
    5:0.05
    6:0.09
    7:0.11
    8:0.04
    9:0.07
    10:0.07
    11:0.07
    Negative Logits
    �醒
    -1.76
    uggle
    -1.75
     beforehand
    -1.75
    aunder
    -1.58
    "/>
    -1.51
    Interstitial
    -1.43
    isine
    -1.42
    oof
    -1.37
    illes
    -1.34
    endif
    -1.33
    POSITIVE LOGITS
     columnist
    1.31
     Column
    1.27
     blogger
    1.24
    Progress
    1.19
     Redmond
    1.18
     Judge
    1.15
     Asc
    1.14
    URR
    1.13
     commenter
    1.13
     Univers
    1.13
    Activations Density 0.018%

    No Known Activations