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

    Neuronpedia

    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. 9-ATT-KK
    11. 520
    Prev
    Next
    INDEX
    Explanations

    instances of social and legal issues related to human rights and criminality

    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
    0:0.30
    1:0.01
    2:0.15
    3:0.11
    4:0.02
    5:0.08
    6:0.02
    7:0.04
    8:0.05
    9:0.01
    10:0.11
    11:0.02
    Negative Logits
    ullivan
    -2.33
     helium
    -2.19
     refresh
    -2.09
    inger
    -2.06
    ゴン
    -2.05
     specs
    -2.00
     Wedding
    -1.98
    aline
    -1.97
     sensing
    -1.97
     Editors
    -1.96
    POSITIVE LOGITS
     impunity
    3.35
     perpetrated
    3.08
     rampant
    2.80
     insidious
    2.80
     pract
    2.67
     pervasive
    2.65
     abhor
    2.64
     endemic
    2.63
     practiced
    2.61
     prevalent
    2.46
    Activations Density 0.110%

    No Known Activations