© 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. 10126
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal charges and 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
    0:0.08
    1:0.24
    2:0.03
    3:0.04
    4:0.05
    5:0.04
    6:0.13
    7:0.03
    8:0.04
    9:0.16
    10:0.02
    11:0.09
    Negative Logits
    ucha
    -3.22
    ECK
    -3.08
    ь
    -2.81
     CHAR
    -2.79
    izoph
    -2.68
    UCT
    -2.64
     CHO
    -2.63
    LINE
    -2.62
    cil
    -2.61
     FORM
    -2.61
    POSITIVE LOGITS
    related
    4.80
     Related
    4.62
     related
    4.52
    Related
    4.17
     unrelated
    3.59
     relates
    3.56
    obic
    3.30
     Blackwell
    3.24
    associated
    3.20
    linked
    3.13
    Activations Density 0.002%

    No Known Activations