© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 5007
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases indicating limitations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.02
    2:0.09
    3:0.17
    4:0.05
    5:0.21
    6:0.05
    7:0.09
    8:0.07
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
     enforce
    -3.49
     prohibitions
    -3.49
     repeal
    -3.46
     mandatory
    -3.26
     protections
    -3.26
     restrictive
    -3.23
     exemptions
    -3.19
     enforced
    -3.18
     mandated
    -3.17
     coercive
    -3.16
    POSITIVE LOGITS
     Witches
    3.00
    Legend
    2.84
     Chess
    2.78
     Sas
    2.75
     Wonders
    2.71
     Hers
    2.70
    �
    2.69
     Bigfoot
    2.59
     Mysterious
    2.58
     Shak
    2.57
    Activations Density 0.012%

    No Known Activations