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. 3-ATT-KK
    6. 10562
    Prev
    Next
    INDEX
    Explanations

    phrases and actions related to agreements, commitments, and contractual obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.05
    2:0.15
    3:0.06
    4:0.02
    5:0.04
    6:0.06
    7:0.09
    8:0.17
    9:0.14
    10:0.08
    11:0.07
    Negative Logits
    isible
    -1.35
    imming
    -1.12
     manif
    -1.07
     bubbles
    -1.05
    abwe
    -1.03
    rites
    -1.02
    stitial
    -1.01
     mirac
    -0.99
    prone
    -0.98
    aturated
    -0.97
    POSITIVE LOGITS
    ALSE
    1.23
     extradition
    1.19
     consent
    1.16
     Consent
    1.11
     exclus
    1.10
    AFTA
    1.09
     assurances
    1.08
     confidentiality
    1.07
     indefinite
    1.06
     waive
    1.06
    Activations Density 0.020%

    No Known Activations