© 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. 3004
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate actions or measures that have been taken or need to be taken

    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
    0:0.35
    1:0.01
    2:0.17
    3:0.09
    4:0.03
    5:0.04
    6:0.01
    7:0.04
    8:0.02
    9:0.01
    10:0.14
    11:0.02
    Negative Logits
    Winner
    -2.69
     Writers
    -2.65
    Writ
    -2.64
     Fiction
    -2.64
     cartoon
    -2.51
     columnist
    -2.49
     slot
    -2.46
     pund
    -2.44
    �
    -2.41
    Column
    -2.41
    POSITIVE LOGITS
     steps
    3.92
     Steps
    3.86
     precaution
    3.25
    autions
    3.10
     precautions
    3.09
     undertaken
    3.06
     STEP
    2.95
     Step
    2.91
     mitigation
    2.88
    steps
    2.83
    Activations Density 0.018%

    No Known Activations