© 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. 21083
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to robbery and assaults

    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
    1:0.07
    2:0.13
    3:0.11
    4:0.07
    5:0.12
    6:0.05
    7:0.09
    8:0.04
    9:0.04
    10:0.09
    11:0.08
    Negative Logits
    etheless
    -2.54
     «
    -2.38
    abad
    -2.22
    eday
    -2.14
     Clarkson
    -2.14
     inquest
    -2.11
    >[
    -2.07
     }}
    -2.04
     Fn
    -2.03
    isSpecialOrderable
    -2.01
    POSITIVE LOGITS
     purs
    2.50
    AIDS
    2.13
     victim
    2.08
    dollar
    2.06
    WB
    2.03
     HIV
    2.01
     AIDS
    1.99
     purse
    1.97
     wallets
    1.97
    wine
    1.92
    Activations Density 0.024%

    No Known Activations