© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 28322
    Prev
    Next
    INDEX
    Explanations

    terms related to transformation across various sectors and contexts

    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
    2:0.05
    3:0.09
    4:0.30
    5:0.04
    6:0.03
    7:0.17
    8:0.04
    9:0.05
    10:0.06
    11:0.07
    Negative Logits
     caveats
    -1.93
    wcsstore
    -1.76
     caveat
    -1.61
    cooked
    -1.60
     workaround
    -1.55
     McGr
    -1.52
     proof
    -1.49
    EEEE
    -1.49
     disclaimer
    -1.47
    ────
    -1.46
    POSITIVE LOGITS
     fortunes
    1.79
     landscape
    1.67
     ecosystems
    1.61
     world
    1.59
     society
    1.59
     senses
    1.56
     ecology
    1.56
     worlds
    1.55
     generations
    1.52
    planet
    1.50
    Activations Density 0.011%

    No Known Activations