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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20674
    Prev
    Next
    INDEX
    Explanations

    significant occurrences of the word "chair" in various contexts

    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
    1:0.03
    2:0.07
    3:0.05
    4:0.03
    5:0.04
    6:0.20
    7:0.03
    8:0.06
    9:0.29
    10:0.03
    11:0.04
    Negative Logits
     Xiaomi
    -3.72
     Gale
    -3.69
     Gaddafi
    -3.61
     Canal
    -3.60
     Sail
    -3.49
     Kali
    -3.40
     Mozilla
    -3.39
     Bungie
    -3.38
     Aval
    -3.29
     Mash
    -3.29
    POSITIVE LOGITS
     chair
    7.03
     Chair
    6.67
     chairs
    6.56
    chair
    6.23
    chairs
    6.08
    Chair
    5.88
     wheelchair
    5.59
     Bowen
    4.22
     Schultz
    4.21
    itsch
    3.91
    Activations Density 0.002%

    No Known Activations