© 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. 38065
    Prev
    Next
    INDEX
    Explanations

    references to government actions and regulations

    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
    0:0.02
    1:0.03
    2:0.05
    3:0.43
    4:0.06
    5:0.06
    6:0.03
    7:0.03
    8:0.04
    9:0.08
    10:0.07
    11:0.05
    Negative Logits
    Sov
    -2.12
    paralle
    -2.07
    Ire
    -2.03
    SourceFile
    -1.93
     sooner
    -1.92
    )."
    -1.92
    albeit
    -1.87
    ··
    -1.85
    ...)
    -1.83
    !).
    -1.83
    POSITIVE LOGITS
     Photograph
    1.81
     Employees
    1.74
    ?:
    1.73
    ':
    1.72
     ⓘ
    1.66
    intendent
    1.63
     Photos
    1.62
     Released
    1.60
     Gets
    1.59
     Possible
    1.57
    Activations Density 0.012%

    No Known Activations