© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 29863
    Prev
    Next
    INDEX
    Explanations

    phrases that involve the questioning of methods or processes

    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
    0:0.17
    1:0.02
    2:0.12
    3:0.04
    4:0.06
    5:0.06
    6:0.03
    7:0.05
    8:0.16
    9:0.08
    10:0.06
    11:0.08
    Negative Logits
    alysed
    -1.92
    ocre
    -1.83
    ixed
    -1.76
    OOOO
    -1.74
    iazep
    -1.70
    sole
    -1.67
    unic
    -1.63
    adra
    -1.61
    gged
    -1.61
    luent
    -1.53
    POSITIVE LOGITS
    erness
    1.72
     impressions
    1.69
     perceptions
    1.65
    ibilities
    1.64
     timelines
    1.62
     misconceptions
    1.60
     Availability
    1.57
     specifics
    1.57
     IPM
    1.53
     prospects
    1.52
    Activations Density 0.027%

    No Known Activations