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. 7-ATT-KK
    6. 9032
    Prev
    Next
    INDEX
    Explanations

    phrases regarding responsibility or accountability in actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.11
    2:0.12
    3:0.04
    4:0.02
    5:0.04
    6:0.06
    7:0.06
    8:0.05
    9:0.04
    10:0.36
    11:0.03
    Negative Logits
     Slater
    -2.29
     Lars
    -2.20
    MD
    -2.16
     NG
    -2.07
    PATH
    -2.06
    LL
    -2.05
     Merch
    -2.03
     CHRIST
    -2.01
     Laurent
    -1.99
     ARC
    -1.99
    POSITIVE LOGITS
     consideration
    3.22
    consider
    3.18
     consider
    3.04
    urdue
    2.99
     contemplate
    2.97
     Consider
    2.96
     considered
    2.81
    Consider
    2.77
    uyomi
    2.76
     considers
    2.64
    Activations Density 0.012%

    No Known Activations