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. 3-ATT-KK
    6. 8519
    Prev
    Next
    INDEX
    Explanations

    questions and statements regarding existence and the effectiveness of various actions or things

    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
    0:0.01
    1:0.08
    2:0.15
    3:0.03
    4:0.01
    5:0.03
    6:0.09
    7:0.11
    8:0.13
    9:0.13
    10:0.05
    11:0.12
    Negative Logits
    Kings
    -1.37
     [+]
    -1.29
     [|
    -1.26
     @@
    -1.24
     Mart
    -1.18
     oak
    -1.17
     Macintosh
    -1.10
    Mac
    -1.08
    erton
    -1.08
     Pathfinder
    -1.07
    POSITIVE LOGITS
     anymore
    1.89
     nor
    1.74
     Beir
    1.64
     slightest
    1.63
    necess
    1.54
     obser
    1.52
     anybody
    1.50
    ynt
    1.41
    berra
    1.40
    jri
    1.37
    Activations Density 0.053%

    No Known Activations