© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 17078
    Prev
    Next
    INDEX
    Explanations

    references to individuals and organizations involved in criminal activities

    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
    0:0.07
    1:0.03
    2:0.02
    3:0.08
    4:0.01
    5:0.03
    6:0.17
    7:0.03
    8:0.03
    9:0.44
    10:0.02
    11:0.01
    Negative Logits
     Squ
    -3.70
     Rew
    -3.67
     Huck
    -3.60
     Fet
    -3.49
     FEC
    -3.34
    Squ
    -3.31
     Fallen
    -3.21
    Rew
    -3.20
     Fold
    -3.20
    fet
    -3.17
    POSITIVE LOGITS
    son
    7.48
    SON
    6.57
     Stevenson
    5.17
     Samson
    4.99
    erson
    4.64
    Son
    4.49
    inson
    4.42
     Stark
    4.39
     Son
    4.22
    ERSON
    4.19
    Activations Density 0.002%

    No Known Activations