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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9088
    Prev
    Next
    INDEX
    Explanations

    phrases related to the uncertainty or change in regulations and policies

    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
    0:0.08
    1:0.05
    2:0.01
    3:0.12
    4:0.09
    5:0.06
    6:0.05
    7:0.02
    8:0.32
    9:0.09
    10:0.04
    11:0.02
    Negative Logits
    CHO
    -2.11
    aturally
    -1.99
    heat
    -1.79
     Solitaire
    -1.78
     decentral
    -1.71
    ��
    -1.62
    ocial
    -1.62
    galitarian
    -1.61
    uming
    -1.60
    zin
    -1.59
    POSITIVE LOGITS
     indicates
    2.29
     confirms
    2.17
     mentions
    2.15
     attest
    2.05
     indicate
    2.03
     references
    2.03
     confirm
    1.92
     illustrates
    1.90
     discl
    1.90
     cites
    1.89
    Activations Density 0.005%

    No Known Activations