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. 11311
    Prev
    Next
    INDEX
    Explanations

    key concepts and relationships related to risk, instability, and decision-making in political and social 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
    0:0.04
    1:0.06
    2:0.08
    3:0.20
    4:0.06
    5:0.08
    6:0.02
    7:0.12
    8:0.05
    9:0.02
    10:0.15
    11:0.06
    Negative Logits
    Medium
    -3.08
    izont
    -2.99
    requires
    -2.80
     unfocusedRange
    -2.71
    medium
    -2.59
     Alternatively
    -2.57
     corresponds
    -2.55
    ":[{"
    -2.53
    folio
    -2.52
    eger
    -2.50
    POSITIVE LOGITS
     suicides
    3.27
     scandals
    3.17
     murders
    2.94
     riots
    2.92
     arrests
    2.88
     looting
    2.85
     lawsuits
    2.84
     failures
    2.82
     controversies
    2.81
     deaths
    2.79
    Activations Density 0.192%

    No Known Activations