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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 13780
    Prev
    Next
    INDEX
    Explanations

    martial arts techniques and instructions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.04
    2:0.16
    3:0.11
    4:0.07
    5:0.16
    6:0.03
    7:0.03
    8:0.09
    9:0.08
    10:0.07
    11:0.03
    Negative Logits
    anchester
    -1.14
    ktop
    -1.11
    wagen
    -1.06
    uncture
    -1.04
    arie
    -1.03
    atu
    -1.01
     Wick
    -1.01
    hement
    -1.00
     Gors
    -0.99
    emetery
    -0.99
    POSITIVE LOGITS
    -+
    1.52
     alike
    1.28
    yahoo
    1.14
    acters
    1.13
     combo
    1.09
    Skill
    1.06
     combinations
    1.01
     combos
    0.98
    Yo
    0.94
    catentry
    0.94
    Activations Density 0.023%

    No Known Activations