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. 3166
    Prev
    Next
    INDEX
    Explanations

    details about characters and their attributes in games

    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
    1:0.03
    2:0.07
    3:0.27
    4:0.02
    5:0.07
    6:0.01
    7:0.15
    8:0.04
    9:0.01
    10:0.21
    11:0.01
    Negative Logits
    windows
    -2.28
    aults
    -2.19
    berra
    -2.19
    cats
    -2.13
    boys
    -2.08
     wildfires
    -2.08
     hurricanes
    -2.06
    hawks
    -2.05
    adas
    -2.03
    andals
    -2.00
    POSITIVE LOGITS
     individually
    2.89
     corresponding
    2.81
     varying
    2.72
     apiece
    2.55
     predetermined
    2.52
     randomly
    2.44
     identifier
    2.44
     each
    2.38
     graded
    2.36
     differently
    2.34
    Activations Density 0.161%

    No Known Activations