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. 27427
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and relationships

    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
    0:0.01
    1:0.02
    2:0.09
    3:0.12
    4:0.34
    5:0.02
    6:0.13
    7:0.06
    8:0.02
    9:0.02
    10:0.05
    11:0.06
    Negative Logits
    idate
    -1.59
    successfully
    -1.58
    isively
    -1.48
    undai
    -1.44
    OTA
    -1.41
    eto
    -1.35
    appropriately
    -1.34
    姫
    -1.32
     accordingly
    -1.31
    ギ
    -1.31
    POSITIVE LOGITS
     curiosity
    1.59
     pure
    1.42
     continuation
    1.41
    htaking
    1.39
     coincidence
    1.38
     intuition
    1.36
     ticking
    1.35
     exceptional
    1.31
     scrib
    1.28
     essentials
    1.24
    Activations Density 0.062%

    No Known Activations