© 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. 9-ATT-KK
    11. 471
    Prev
    Next
    INDEX
    Explanations

    phrases related to decisions and their implications

    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
    0:0.04
    1:0.01
    2:0.06
    3:0.12
    4:0.02
    5:0.06
    6:0.02
    7:0.04
    8:0.02
    9:0.01
    10:0.53
    11:0.02
    Negative Logits
    stores
    -1.93
    aura
    -1.91
     dominates
    -1.79
    rench
    -1.78
     haunt
    -1.77
    ife
    -1.75
    cart
    -1.75
    world
    -1.74
    rome
    -1.73
    イト
    -1.71
    POSITIVE LOGITS
     because
    3.24
    because
    3.23
     precaution
    2.95
     purely
    2.93
    Because
    2.88
     due
    2.78
     solely
    2.75
     purpose
    2.71
     Because
    2.65
     intending
    2.63
    Activations Density 1.046%

    No Known Activations