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. 22262
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the"

    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
    0:0.06
    1:0.01
    2:0.12
    3:0.12
    4:0.03
    5:0.12
    6:0.05
    7:0.07
    8:0.07
    9:0.08
    10:0.14
    11:0.07
    Negative Logits
    ��
    -1.41
    reach
    -1.31
    speak
    -1.19
    alloc
    -1.13
    antis
    -1.07
    �
    -1.03
    acts
    -0.99
    �
    -0.98
    �
    -0.96
    aband
    -0.95
    POSITIVE LOGITS
    liest
    1.40
    iest
    1.27
     Authors
    1.25
     architect
    1.15
     heirs
    1.13
    cients
    1.10
     oldest
    1.03
     nearest
    1.02
     portion
    1.01
     architects
    0.99
    Activations Density 0.267%

    No Known Activations