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. 7647
    Prev
    Next
    INDEX
    Explanations

    the word "only" indicating exclusivity or singularity

    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
    4:0.08
    5:0.07
    6:0.08
    7:0.08
    8:0.08
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
    TRUMP
    -3.04
    Administ
    -2.98
    amazon
    -2.92
    Disney
    -2.70
    GOP
    -2.67
    utan
    -2.65
    launch
    -2.64
    oku
    -2.59
     haw
    -2.58
    latable
    -2.54
    POSITIVE LOGITS
     Lv
    2.97
     Reich
    2.72
     Held
    2.63
     Cologne
    2.57
     Yug
    2.52
     Rh
    2.47
     IGF
    2.45
    ngth
    2.44
     Hung
    2.40
     Feldman
    2.40
    Activations Density 0.000%

    No Known Activations