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. 27440
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the presence or existence of something

    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
    0:0.02
    1:0.02
    2:0.09
    3:0.06
    4:0.14
    5:0.02
    6:0.04
    7:0.29
    8:0.02
    9:0.04
    10:0.08
    11:0.13
    Negative Logits
    ilage
    -1.49
     appre
    -1.46
     endeav
    -1.35
     endeavors
    -1.35
     ende
    -1.34
    aciously
    -1.32
    ancial
    -1.25
    NBC
    -1.25
    RG
    -1.25
    ��
    -1.22
    POSITIVE LOGITS
    Reviewer
    1.45
    abo
    1.34
     oneself
    1.32
    mite
    1.31
     Qué
    1.30
    ouls
    1.28
     Nanto
    1.28
     presence
    1.21
     witnesses
    1.18
     parentheses
    1.17
    Activations Density 0.003%

    No Known Activations