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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 195
    Prev
    Next
    INDEX
    Explanations

    data related to security, breaches, and compliance in the context of digital information systems

    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
    0:0.21
    1:0.02
    2:0.29
    3:0.07
    4:0.02
    5:0.10
    6:0.04
    7:0.04
    8:0.06
    9:0.03
    10:0.03
    11:0.03
    Negative Logits
    Dialogue
    -2.78
     pacif
    -2.55
    bane
    -2.45
    Nit
    -2.41
     synthesis
    -2.37
     Enemies
    -2.34
    Prop
    -2.29
     Lethal
    -2.28
    gom
    -2.27
    arij
    -2.27
    POSITIVE LOGITS
    ifax
    4.76
     breach
    3.27
     impacted
    3.17
     outage
    3.16
     lenders
    3.04
     credit
    3.02
     lender
    2.97
     disclosing
    2.97
     retailer
    2.94
     creditor
    2.94
    Activations Density 0.003%

    No Known Activations