© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 37525
    Prev
    Next
    INDEX
    Explanations

    references to monetary amounts and financial figures

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.19
    1:0.09
    2:0.05
    3:0.05
    4:0.04
    5:0.17
    6:0.02
    7:0.02
    8:0.12
    9:0.06
    10:0.09
    11:0.06
    Negative Logits
    trap
    -2.26
    chall
    -2.05
    itsch
    -2.01
    adelphia
    -1.91
    fork
    -1.87
    keye
    -1.84
    omnia
    -1.81
    plot
    -1.73
    estone
    -1.73
    shake
    -1.73
    POSITIVE LOGITS
     certs
    1.67
     TBD
    1.62
     33
    1.53
     effic
    1.52
     Ibid
    1.52
     ¥
    1.51
     29
    1.50
     129
    1.48
     1862
    1.48
     358
    1.47
    Activations Density 0.003%

    No Known Activations