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. 44378
    Prev
    Next
    INDEX
    Explanations

    bracketed text or items within parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.04
    1:0.02
    2:0.14
    3:0.10
    4:0.05
    5:0.07
    6:0.23
    7:0.03
    8:0.09
    9:0.06
    10:0.05
    11:0.08
    Negative Logits
    natureconservancy
    -1.72
    Rush
    -1.68
    bryce
    -1.64
    �
    -1.56
    upt
    -1.55
    patch
    -1.54
    aea
    -1.54
    Scar
    -1.45
    ��
    -1.42
    ky
    -1.41
    POSITIVE LOGITS
     meanwhile
    1.55
    enhagen
    1.49
     compet
    1.42
     horizont
    1.42
     Monaco
    1.41
     Petersen
    1.35
    puter
    1.34
     Wilkinson
    1.32
    PLIED
    1.32
    roleum
    1.28
    Activations Density 0.002%

    No Known Activations