© 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. 39612
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate a high level of agreement or consensus

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.08
    3:0.12
    4:0.16
    5:0.06
    6:0.18
    7:0.03
    8:0.05
    9:0.09
    10:0.07
    11:0.04
    Negative Logits
     Galile
    -1.13
     Gaz
    -1.07
     Nare
    -1.06
    glers
    -1.03
    iership
    -1.02
     Pil
    -1.02
     Inqu
    -1.00
     Seym
    -1.00
     Tir
    -1.00
    othal
    -0.99
    POSITIVE LOGITS
    unknown
    1.25
    版
    1.24
    channelAvailability
    1.22
    999
    1.21
    sein
    1.21
    icio
    1.17
    imo
    1.17
    edit
    1.17
    Rand
    1.15
    ulously
    1.15
    Activations Density 0.170%

    No Known Activations