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. 3128
    Prev
    Next
    INDEX
    Explanations

    instances of serious crimes and their consequences

    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
    2:0.05
    3:0.05
    4:0.06
    5:0.05
    6:0.25
    7:0.05
    8:0.06
    9:0.18
    10:0.04
    11:0.05
    Negative Logits
     Miranda
    -3.47
     lich
    -3.23
     Droid
    -3.13
    minist
    -3.07
     droid
    -3.07
     decriminal
    -3.02
    Republic
    -3.00
    "></
    -2.96
    iPhone
    -2.93
     lev
    -2.92
    POSITIVE LOGITS
     Woods
    9.50
    woods
    5.37
     woods
    5.24
    Wood
    5.06
     Golf
    4.12
     Bonds
    4.09
     Trails
    4.01
     Trees
    3.97
     Tiger
    3.92
     golf
    3.76
    Activations Density 0.004%

    No Known Activations