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. 7566
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with color and planning

    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
    0:0.06
    1:0.14
    2:0.07
    3:0.05
    4:0.04
    5:0.04
    6:0.21
    7:0.03
    8:0.02
    9:0.24
    10:0.03
    11:0.02
    Negative Logits
     Manit
    -3.39
     Ard
    -3.39
     Kane
    -3.33
     Barrett
    -3.30
     NAS
    -3.25
     Bren
    -3.21
     AA
    -3.20
     Trib
    -3.14
     Bil
    -3.13
     Adin
    -3.09
    POSITIVE LOGITS
    change
    5.96
    Change
    5.78
     Change
    5.47
     Changed
    5.04
    changes
    4.99
     change
    4.83
     changed
    4.49
    Changes
    4.47
    changing
    4.37
    Changing
    4.36
    Activations Density 0.004%

    No Known Activations