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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14783
    Prev
    Next
    INDEX
    Explanations

    details related to criminal activity and investigative processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.14
    2:0.04
    3:0.04
    4:0.03
    5:0.03
    6:0.05
    7:0.34
    8:0.02
    9:0.06
    10:0.10
    11:0.04
    Negative Logits
     Weed
    -2.74
     Finch
    -2.51
     Dent
    -2.22
     hect
    -2.20
     fung
    -2.18
     Foss
    -2.15
     Cann
    -2.10
     Fundamental
    -2.06
     stakes
    -2.00
     disreg
    -1.99
    POSITIVE LOGITS
    dylib
    2.97
    javascript
    2.62
    writing
    2.54
    ItemTracker
    2.52
    hari
    2.51
    NJ
    2.39
    ía
    2.33
    washer
    2.33
    ivan
    2.28
    Posted
    2.28
    Activations Density 0.004%

    No Known Activations