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. 2-ATT-KK
    6. 13872
    Prev
    Next
    INDEX
    Explanations

    words relating to commercial products and promotions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.12
    3:0.04
    4:0.30
    5:0.07
    6:0.02
    7:0.02
    8:0.12
    9:0.12
    10:0.05
    11:0.02
    Negative Logits
    ��
    -1.55
    irez
    -1.43
    interstitial
    -1.39
    WithNo
    -1.36
    ��
    -1.35
    ternity
    -1.33
    UTF
    -1.27
    STD
    -1.25
    Wik
    -1.24
     Archdemon
    -1.24
    POSITIVE LOGITS
    yip
    1.51
    neau
    1.41
    ths
    1.33
    lishes
    1.31
     snap
    1.25
    akuya
    1.22
     aloud
    1.19
     Peel
    1.18
     favourites
    1.18
    ches
    1.16
    Activations Density 0.005%

    No Known Activations