Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11246
    Prev
    Next
    INDEX
    Explanations

    phrases indicating accountability and scrutiny regarding actions and policies

    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
    1:0.02
    2:0.06
    3:0.18
    4:0.02
    5:0.07
    6:0.02
    7:0.05
    8:0.03
    9:0.01
    10:0.39
    11:0.04
    Negative Logits
     tomorrow
    -2.19
     WHEN
    -2.16
     THEN
    -1.95
    when
    -1.94
    Econom
    -1.93
     arises
    -1.85
     anymore
    -1.84
    throp
    -1.83
    ]]
    -1.80
     Writer
    -1.79
    POSITIVE LOGITS
     extensively
    2.62
     numerous
    2.39
     extensive
    2.35
     repeatedly
    2.34
    ��極
    2.32
    issues
    2.18
    sever
    2.16
     unsuccessfully
    2.14
    multiple
    2.13
     multiple
    2.12
    Activations Density 0.599%

    No Known Activations