© 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. 38365
    Prev
    Next
    INDEX
    Explanations

    statements about significant health issues or life-threatening conditions

    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
    0:0.05
    1:0.01
    2:0.08
    3:0.13
    4:0.06
    5:0.07
    6:0.01
    7:0.04
    8:0.10
    9:0.12
    10:0.18
    11:0.10
    Negative Logits
    ]"
    -1.36
    rule
    -1.23
    ample
    -1.23
    omach
    -1.22
    )"
    -1.20
    efined
    -1.19
    "…
    -1.17
    ]'
    -1.15
     objected
    -1.15
    aters
    -1.15
    POSITIVE LOGITS
     blogging
    1.35
     gym
    1.33
     hopes
    1.25
     retiring
    1.24
    ------------------------------------------------
    1.22
     freelance
    1.21
     dreaming
    1.21
     volunteering
    1.19
     awaiting
    1.18
     rehab
    1.15
    Activations Density 0.423%

    No Known Activations