© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22913
    Prev
    Next
    INDEX
    Explanations

    references to military, technology, data management, and healthcare in different contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    keywords related to information access and control issues across various domains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.05
    2:0.06
    3:0.07
    4:0.04
    5:0.08
    6:0.02
    7:0.03
    8:0.34
    9:0.10
    10:0.06
    11:0.03
    Negative Logits
    ussy
    -1.36
    aughed
    -1.35
    ochet
    -1.34
    pole
    -1.30
    ovember
    -1.29
     Dmitry
    -1.29
    ammy
    -1.29
    abbit
    -1.28
     Seym
    -1.27
    illon
    -1.26
    POSITIVE LOGITS
     substr
    1.50
    resources
    1.49
     foothold
    1.46
    TEXTURE
    1.38
     credentials
    1.33
    20439
    1.32
    artifacts
    1.31
     consent
    1.30
     databases
    1.30
     gateway
    1.30
    Activations Density 0.037%

    No Known Activations