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. 9127
    Prev
    Next
    INDEX
    Explanations

    temporal references related to events or 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
    0:0.06
    1:0.04
    2:0.01
    3:0.10
    4:0.11
    5:0.07
    6:0.03
    7:0.02
    8:0.45
    9:0.04
    10:0.01
    11:0.01
    Negative Logits
     Ratings
    -1.90
     booths
    -1.67
    hd
    -1.64
     sim
    -1.59
     unbeliev
    -1.57
    nai
    -1.55
     efficacy
    -1.54
     Simulator
    -1.54
    ihu
    -1.51
    aming
    -1.50
    POSITIVE LOGITS
    ffe
    2.08
     departing
    2.00
     Travel
    1.88
     Airl
    1.84
     haste
    1.83
     headed
    1.83
    travel
    1.82
    ucket
    1.82
     departed
    1.80
    20439
    1.73
    Activations Density 0.064%

    No Known Activations