© 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. 11153
    Prev
    Next
    INDEX
    Explanations

    references to legal incidents and charges related to drug offenses

    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
    0:0.08
    1:0.01
    2:0.05
    3:0.03
    4:0.05
    5:0.03
    6:0.31
    7:0.04
    8:0.07
    9:0.24
    10:0.01
    11:0.02
    Negative Logits
    ohyd
    -4.20
    paren
    -4.06
     membranes
    -3.82
    hub
    -3.81
     circum
    -3.64
     Bucc
    -3.64
    BIP
    -3.53
     squid
    -3.52
    768
    -3.49
     Bulgarian
    -3.49
    POSITIVE LOGITS
     Taylor
    12.12
    Taylor
    11.93
     Tay
    6.25
    aylor
    5.82
     Reilly
    5.05
     Scion
    4.79
     Swift
    4.78
     Tinker
    4.76
     Travis
    4.39
     Tanner
    4.31
    Activations Density 0.019%

    No Known Activations