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. 13787
    Prev
    Next
    INDEX
    Explanations

    code snippets related to image processing using specific syntax and variables

    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
    0:0.06
    1:0.05
    2:0.11
    3:0.08
    4:0.06
    5:0.10
    6:0.05
    7:0.05
    8:0.14
    9:0.12
    10:0.09
    11:0.03
    Negative Logits
    emouth
    -1.35
    ggles
    -1.34
    antz
    -1.30
    _>
    -1.30
    illery
    -1.29
    ighters
    -1.28
    veland
    -1.26
    Ctrl
    -1.24
    iets
    -1.24
    ernel
    -1.21
    POSITIVE LOGITS
    セ
    1.48
    ロ
    1.26
     �
    1.17
     {{
    1.14
    カ
    1.14
    xxxxxxxx
    1.13
    ク
    1.13
    ن
    1.13
     EPA
    1.12
    版
    1.12
    Activations Density 0.006%

    No Known Activations