© 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. 39483
    Prev
    Next
    INDEX
    Explanations

    instances of numerical data, particularly related to temperatures or measurements

    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
    0:0.11
    1:0.09
    2:0.08
    3:0.07
    4:0.04
    5:0.11
    6:0.07
    7:0.04
    8:0.12
    9:0.09
    10:0.05
    11:0.05
    Negative Logits
    pai
    -1.63
    eatures
    -1.51
    volt
    -1.50
    zie
    -1.49
    mA
    -1.49
    amera
    -1.46
    edition
    -1.44
    aste
    -1.39
    comfort
    -1.39
    Login
    -1.39
    POSITIVE LOGITS
     Kro
    1.63
     Ninth
    1.51
     Levant
    1.49
     Moss
    1.49
     PTS
    1.45
     etc
    1.44
     Conclusion
    1.44
    osure
    1.41
     GL
    1.40
     sake
    1.38
    Activations Density 0.000%

    No Known Activations