© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 2182
    Prev
    Next
    INDEX
    Explanations

    references to societal norms or behaviors regarding acceptance and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.08
    1:0.02
    2:0.03
    3:0.04
    4:0.18
    5:0.12
    6:0.30
    7:0.01
    8:0.05
    9:0.03
    10:0.05
    11:0.02
    Negative Logits
    ��
    -1.49
    ronics
    -1.31
     Pric
    -1.23
     parap
    -1.23
     medi
    -1.20
    ctors
    -1.19
     prelim
    -1.19
    Plot
    -1.18
    Actor
    -1.18
     Operator
    -1.18
    POSITIVE LOGITS
    won
    1.66
    ean
    1.61
    yden
    1.50
    dk
    1.45
    xi
    1.45
    schild
    1.44
    velt
    1.41
    echo
    1.40
    erent
    1.40
    ELY
    1.40
    Activations Density 0.006%

    No Known Activations