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. 22248
    Prev
    Next
    INDEX
    Explanations

    the repetition of the phrase "of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.05
    1:0.02
    2:0.19
    3:0.04
    4:0.36
    5:0.04
    6:0.03
    7:0.03
    8:0.05
    9:0.07
    10:0.04
    11:0.02
    Negative Logits
    フォ
    -1.70
    ouch
    -1.66
    �
    -1.56
    trak
    -1.55
     Lover
    -1.47
    ington
    -1.47
    Home
    -1.47
    方
    -1.45
    rongh
    -1.41
    ilet
    -1.38
    POSITIVE LOGITS
     absurdity
    1.91
     exhaustion
    1.62
     negativity
    1.57
     intoxication
    1.54
     abstraction
    1.50
     incomp
    1.49
     contradictions
    1.48
     humour
    1.47
    culus
    1.46
     error
    1.44
    Activations Density 0.014%

    No Known Activations