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

    Neuronpedia

    Jacobian LensNEW
    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. 6390
    Prev
    Next
    INDEX
    Explanations

    references to criminal activity and individuals involved in such incidents

    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
    0:0.02
    1:0.01
    2:0.04
    3:0.07
    4:0.03
    5:0.05
    6:0.03
    7:0.03
    8:0.04
    9:0.07
    10:0.45
    11:0.11
    Negative Logits
     ambassadors
    -2.04
     championships
    -1.94
     divisions
    -1.94
     conventions
    -1.92
     arenas
    -1.86
     champions
    -1.84
     Awards
    -1.80
     presidents
    -1.77
     prizes
    -1.76
     Directors
    -1.74
    POSITIVE LOGITS
    hid
    2.17
    llah
    2.16
    abwe
    1.80
    ertodd
    1.77
    ullah
    1.77
    bek
    1.72
     Ramirez
    1.71
    REP
    1.67
    furt
    1.67
    hunt
    1.65
    Activations Density 0.403%

    No Known Activations