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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 18970
    Prev
    Next
    INDEX
    Explanations

    elements related to publication details and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.07
    2:0.04
    3:0.08
    4:0.06
    5:0.07
    6:0.08
    7:0.22
    8:0.07
    9:0.10
    10:0.07
    11:0.06
    Negative Logits
    auder
    -2.46
    zar
    -2.36
    aroo
    -2.30
    sch
    -2.16
     Trayvon
    -2.12
     recount
    -2.10
    zsche
    -2.06
    -+-+
    -2.04
    raham
    -2.00
    htaking
    -1.99
    POSITIVE LOGITS
     translated
    2.77
     ported
    2.46
     Manga
    2.32
    ドラ
    2.27
     transl
    2.27
    Released
    2.15
     localization
    2.13
    ilaterally
    2.13
     digitally
    2.11
     downloaded
    2.11
    Activations Density 0.002%

    No Known Activations