© 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. 2-ATT-KK
    11. 16158
    Prev
    Next
    INDEX
    Explanations

    words related to narratives or storytelling, particularly mentioning people and events

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.07
    1:0.03
    2:0.14
    3:0.07
    4:0.24
    5:0.04
    6:0.02
    7:0.03
    8:0.12
    9:0.12
    10:0.04
    11:0.02
    Negative Logits
    linked
    -1.15
     google
    -1.15
    \-
    -1.06
    edia
    -1.05
     contrace
    -1.05
    ramid
    -1.04
    chart
    -1.03
     moderator
    -1.02
    usal
    -1.01
     PG
    -0.99
    POSITIVE LOGITS
    gling
    1.40
    ients
    1.33
    iuses
    1.21
    ONES
    1.21
    bos
    1.20
     exceptions
    1.20
    osaurs
    1.17
    grass
    1.16
    glers
    1.15
     desks
    1.13
    Activations Density 0.002%

    No Known Activations