© 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. 9-ATT-KK
    11. 18850
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals related to controversial or criminal actions

    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
    0:0.10
    1:0.02
    2:0.09
    3:0.05
    4:0.05
    5:0.06
    6:0.18
    7:0.05
    8:0.11
    9:0.19
    10:0.02
    11:0.02
    Negative Logits
     mortar
    -3.81
    aghd
    -3.65
    arks
    -3.52
     Optimus
    -3.44
     Galile
    -3.42
     Cree
    -3.38
    merga
    -3.38
    issan
    -3.35
     Spirits
    -3.33
    glas
    -3.30
    POSITIVE LOGITS
     Epstein
    11.53
    Ep
    6.08
     EB
    4.81
     Theo
    4.43
    EB
    4.24
    eph
    4.15
     Erik
    4.01
     Ep
    3.99
     Podesta
    3.82
     Rubin
    3.74
    Activations Density 0.003%

    No Known Activations