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. 5-ATT-KK
    6. 7193
    Prev
    Next
    INDEX
    Explanations

    variations of proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.25
    2:0.07
    3:0.05
    4:0.02
    5:0.16
    6:0.07
    7:0.03
    8:0.05
    9:0.07
    10:0.03
    11:0.03
    Negative Logits
    ograp
    -1.84
    ographed
    -1.50
    ivated
    -1.42
    retty
    -1.42
     ABS
    -1.38
    chel
    -1.33
    */(
    -1.30
    eatures
    -1.28
    pherd
    -1.23
    model
    -1.22
    POSITIVE LOGITS
    �
    2.16
    �
    2.12
    ��
    2.01
    �
    1.68
    tein
    1.65
    ْ
    1.63
    �
    1.62
    �
    1.62
    ��
    1.61
    �
    1.57
    Activations Density 0.007%

    No Known Activations