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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11449
    Prev
    Next
    INDEX
    Explanations

    details about phone specifications and features

    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
    0:0.22
    1:0.02
    2:0.04
    3:0.11
    4:0.03
    5:0.08
    6:0.03
    7:0.06
    8:0.27
    9:0.02
    10:0.04
    11:0.02
    Negative Logits
     Myr
    -3.10
     Hamm
    -2.79
     Ned
    -2.78
     Gutenberg
    -2.73
     pawn
    -2.65
     Wilmington
    -2.59
     [*]
    -2.56
     dwarves
    -2.53
    minster
    -2.49
     Bastard
    -2.48
    POSITIVE LOGITS
     Huawei
    4.37
     Xiaomi
    4.15
     OnePlus
    4.07
     Qualcomm
    3.96
    Android
    3.83
     Snapdragon
    3.77
     handset
    3.64
     Android
    3.55
    awei
    3.54
    Samsung
    3.52
    Activations Density 0.084%

    No Known Activations