© 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. 10-ATT-KK
    11. 17130
    Prev
    Next
    INDEX
    Explanations

    terms related to financial regulations and monetary contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.04
    3:0.04
    4:0.05
    5:0.38
    6:0.04
    7:0.04
    8:0.02
    9:0.22
    10:0.02
    11:0.06
    Negative Logits
    版
    -3.88
    marine
    -2.75
     refuted
    -2.69
    }}}
    -2.65
     horr
    -2.64
    erson
    -2.58
     lobbied
    -2.55
    warts
    -2.52
     partName
    -2.49
    」
    -2.47
    POSITIVE LOGITS
     can
    3.23
    can
    3.10
     permissible
    3.06
    Can
    3.06
     each
    2.86
     Can
    2.73
    Each
    2.70
     allowable
    2.69
     permitted
    2.61
     possible
    2.53
    Activations Density 0.070%

    No Known Activations