© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10416
    Prev
    Next
    INDEX
    Explanations

    instances of censors or censorship-related terms

    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
    1:0.08
    2:0.07
    3:0.08
    4:0.08
    5:0.09
    6:0.08
    7:0.07
    8:0.09
    9:0.08
    10:0.07
    11:0.07
    Negative Logits
     Jur
    -3.02
     Proto
    -2.98
     Mania
    -2.96
     Royale
    -2.84
     Patri
    -2.83
     Resistance
    -2.81
     Zoro
    -2.80
     Submission
    -2.77
     Participation
    -2.74
     proto
    -2.73
    POSITIVE LOGITS
    spell
    3.13
    ティ
    3.10
    windows
    2.87
     stair
    2.74
    licks
    2.73
    cuts
    2.70
     leaf
    2.67
     overhead
    2.57
     screens
    2.53
    stack
    2.51
    Activations Density 0.000%

    No Known Activations