© 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. 47273
    Prev
    Next
    INDEX
    Explanations

    negations and references to the absence of something

    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
    2:0.10
    3:0.10
    4:0.14
    5:0.02
    6:0.21
    7:0.12
    8:0.03
    9:0.03
    10:0.06
    11:0.07
    Negative Logits
    tain
    -1.51
     mates
    -1.28
    igl
    -1.26
    igi
    -1.24
     Jou
    -1.23
     piety
    -1.22
    Hub
    -1.22
     aloud
    -1.22
     beware
    -1.20
    tained
    -1.20
    POSITIVE LOGITS
    netflix
    1.61
     shortage
    1.57
     裏�
    1.51
    abulary
    1.49
     casualties
    1.45
    ophen
    1.43
    farious
    1.42
     deterioration
    1.37
    pload
    1.36
    escal
    1.35
    Activations Density 0.033%

    No Known Activations