© 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. 10163
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "got" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.04
    3:0.08
    4:0.09
    5:0.06
    6:0.16
    7:0.04
    8:0.06
    9:0.04
    10:0.07
    11:0.24
    Negative Logits
    ortium
    -1.68
    cens
    -1.58
     inaccur
    -1.53
    imeters
    -1.47
     Hebdo
    -1.47
     denotes
    -1.45
     tampering
    -1.44
     separately
    -1.43
     beforehand
    -1.43
    vernment
    -1.42
    POSITIVE LOGITS
    Reviewed
    1.89
    condition
    1.88
     thirsty
    1.77
     grapes
    1.69
    ��
    1.59
     Ratings
    1.54
     brood
    1.53
     Experience
    1.52
    ivation
    1.52
     Virus
    1.51
    Activations Density 0.003%

    No Known Activations