© 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. 21873
    Prev
    Next
    INDEX
    Explanations

    dialogue exchanges and interactions between characters

    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
    0:0.11
    1:0.13
    2:0.09
    3:0.05
    4:0.03
    5:0.12
    6:0.07
    7:0.01
    8:0.08
    9:0.16
    10:0.06
    11:0.03
    Negative Logits
    bilt
    -1.28
    usalem
    -1.24
    tek
    -1.19
    aturday
    -1.19
     wi
    -1.17
     kettle
    -1.16
    ideo
    -1.16
    ®,
    -1.15
     shalt
    -1.13
     awa
    -1.13
    POSITIVE LOGITS
     Hussein
    1.26
    ramer
    1.24
     Pis
    1.18
    asis
    1.13
    Ur
    1.12
     Kramer
    1.10
    uv
    1.08
    —"
    1.08
     Hancock
    1.07
    eering
    1.07
    Activations Density 0.004%

    No Known Activations