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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14526
    Prev
    Next
    INDEX
    Explanations

    phrases related to promotional offers and rewards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.06
    2:0.06
    3:0.05
    4:0.04
    5:0.02
    6:0.38
    7:0.09
    8:0.02
    9:0.04
    10:0.04
    11:0.07
    Negative Logits
    Vill
    -3.26
     Pik
    -2.60
    ��
    -2.53
    conom
    -2.43
    Series
    -2.43
    ibling
    -2.42
    Bal
    -2.42
    capital
    -2.42
    avorite
    -2.40
    panel
    -2.40
    POSITIVE LOGITS
     signing
    8.76
     sign
    7.75
     signed
    7.66
     Sign
    7.64
    sign
    7.25
     Signed
    7.13
    signed
    7.03
    Sign
    6.87
     SIGN
    6.33
     signatures
    6.18
    Activations Density 0.165%

    No Known Activations