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. 3-ATT-KK
    6. 10207
    Prev
    Next
    INDEX
    Explanations

    references to light and its properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.39
    1:0.03
    2:0.04
    3:0.03
    4:0.08
    5:0.06
    6:0.07
    7:0.06
    8:0.04
    9:0.03
    10:0.09
    11:0.03
    Negative Logits
    een
    -1.67
    ctions
    -1.62
    coni
    -1.55
    utor
    -1.55
    ublic
    -1.54
    hire
    -1.53
    rian
    -1.52
    pta
    -1.51
    ee
    -1.43
    adian
    -1.42
    POSITIVE LOGITS
     emitting
    1.50
     Nanto
    1.49
    worms
    1.48
     emanating
    1.48
     orbs
    1.46
     penet
    1.44
     penetrating
    1.44
     pellets
    1.42
     vibrations
    1.39
     intensity
    1.38
    Activations Density 0.086%

    No Known Activations