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. 18677
    Prev
    Next
    INDEX
    Explanations

    phrases related to promises and commitments

    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
    1:0.02
    2:0.21
    3:0.06
    4:0.02
    5:0.04
    6:0.04
    7:0.05
    8:0.02
    9:0.05
    10:0.07
    11:0.02
    Negative Logits
    asus
    -2.93
     Ort
    -2.72
     Wikimedia
    -2.58
    tera
    -2.54
    Wikipedia
    -2.53
    MpServer
    -2.49
    Ctrl
    -2.42
     browse
    -2.32
     cruising
    -2.31
     Scan
    -2.27
    POSITIVE LOGITS
     promise
    4.94
     promises
    4.74
     pledges
    4.51
     pledge
    4.14
     assurances
    4.10
     Promise
    4.10
     commitments
    3.99
     promised
    3.99
     vow
    3.82
     assurance
    3.69
    Activations Density 0.071%

    No Known Activations