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. 44213
    Prev
    Next
    INDEX
    Explanations

    references to user engagement with technology and projects

    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
    0:0.01
    1:0.02
    2:0.11
    3:0.06
    4:0.11
    5:0.02
    6:0.03
    7:0.42
    8:0.03
    9:0.03
    10:0.05
    11:0.07
    Negative Logits
    dragon
    -1.64
    uously
    -1.53
    waters
    -1.42
    ansas
    -1.41
    rimp
    -1.40
    antly
    -1.40
     coasts
    -1.38
    Commerce
    -1.38
    VC
    -1.33
    sect
    -1.33
    POSITIVE LOGITS
     chance
    1.75
     latitude
    1.68
     concess
    1.58
     Lifetime
    1.52
     opportunity
    1.48
     Goodbye
    1.41
     unconditional
    1.40
     taste
    1.40
     preferential
    1.39
     privileges
    1.37
    Activations Density 0.085%

    No Known Activations