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. 13788
    Prev
    Next
    INDEX
    Explanations

    keywords related to political and security issues in Kenya

    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
    0:0.14
    1:0.02
    2:0.24
    3:0.06
    4:0.14
    5:0.05
    6:0.02
    7:0.02
    8:0.06
    9:0.12
    10:0.05
    11:0.02
    Negative Logits
    iferation
    -1.52
    ptoms
    -1.41
    ocious
    -1.23
    mobi
    -1.21
     herbs
    -1.21
    essim
    -1.21
     Flavoring
    -1.20
     Petr
    -1.18
    dylib
    -1.18
     deterior
    -1.18
    POSITIVE LOGITS
     Blackwell
    1.36
    TAG
    1.29
     Territory
    1.26
    tree
    1.22
    REE
    1.20
    thal
    1.17
    canon
    1.14
     Sawyer
    1.14
     Goodwin
    1.14
     Dunham
    1.13
    Activations Density 0.009%

    No Known Activations