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. 9-ATT-KK
    6. 20621
    Prev
    Next
    INDEX
    Explanations

    conjunctions used for connecting clauses or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.08
    2:0.07
    3:0.08
    4:0.07
    5:0.08
    6:0.08
    7:0.08
    8:0.08
    9:0.08
    10:0.09
    11:0.08
    Negative Logits
    �
    -3.25
    LOS
    -2.89
    ˈ
    -2.80
    secure
    -2.73
    Anonymous
    -2.52
    �
    -2.52
     patrol
    -2.49
    �
    -2.48
    retty
    -2.48
    �
    -2.46
    POSITIVE LOGITS
     Mek
    3.30
     Nek
    3.18
     Yen
    3.16
     Aber
    3.04
     Shaman
    2.97
     Karma
    2.93
     Lama
    2.90
     Amp
    2.83
     Kab
    2.82
     Syri
    2.79
    Activations Density 0.000%

    No Known Activations