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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 14067
    Prev
    Next
    INDEX
    Explanations

    keywords related to encryption and software security, such as "key," "generated," "adv," "server," "exchange," and "opens."

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.05
    1:0.05
    2:0.24
    3:0.05
    4:0.07
    5:0.09
    6:0.03
    7:0.04
    8:0.05
    9:0.21
    10:0.05
    11:0.03
    Negative Logits
     Tend
    -1.43
    thinkable
    -1.38
     サーティワン
    -1.33
    PF
    -1.31
    stellar
    -1.31
    hur
    -1.29
    女
    -1.26
    Marie
    -1.25
    ustomed
    -1.25
     Qiao
    -1.23
    POSITIVE LOGITS
     keys
    1.30
     sender
    1.29
     decrypt
    1.28
     enc
    1.27
     ignition
    1.21
     destination
    1.19
    tein
    1.18
    orah
    1.16
     encode
    1.15
     printer
    1.15
    Activations Density 0.017%

    No Known Activations