Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19345
    Prev
    Next
    INDEX
    Explanations

    references to performance, costumes, and presentation elements in various 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
    0:0.01
    1:0.01
    2:0.12
    3:0.04
    4:0.37
    5:0.02
    6:0.09
    7:0.17
    8:0.02
    9:0.02
    10:0.04
    11:0.03
    Negative Logits
    ommel
    -1.87
    iland
    -1.86
    united
    -1.69
    aez
    -1.56
    locked
    -1.55
    RELATED
    -1.55
    SPONSORED
    -1.54
    onica
    -1.53
    soType
    -1.52
    oros
    -1.50
    POSITIVE LOGITS
     excuses
    1.67
     extra
    1.67
     stink
    1.58
     offensive
    1.55
     smokes
    1.51
     mortar
    1.50
     plaster
    1.48
     haste
    1.46
     backup
    1.46
     mascara
    1.46
    Activations Density 0.007%

    No Known Activations