© 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. 5-ATT-KK
    11. 36323
    Prev
    Next
    INDEX
    Explanations

    mentions of law enforcement or specific police actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.05
    2:0.09
    3:0.08
    4:0.08
    5:0.08
    6:0.07
    7:0.07
    8:0.08
    9:0.08
    10:0.08
    11:0.09
    Negative Logits
    Problem
    -1.96
    clerosis
    -1.86
    aus
    -1.78
    artifacts
    -1.77
    ◼
    -1.70
     Worse
    -1.67
    Newsletter
    -1.65
    Interface
    -1.63
    cci
    -1.60
    universal
    -1.60
    POSITIVE LOGITS
     Akron
    2.22
     ILCS
    1.84
     Aub
    1.77
    ibles
    1.75
     Ake
    1.68
     Kass
    1.67
    Keefe
    1.64
     Blair
    1.63
     Glasgow
    1.63
     Abram
    1.58
    Activations Density 0.000%

    No Known Activations