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. 22448
    Prev
    Next
    INDEX
    Explanations

    phrases related to whistleblowing or revealing secret information

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

    instances of whistleblowing and references to deadlines in various contexts

    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
    0:0.09
    1:0.03
    2:0.05
    3:0.10
    4:0.03
    5:0.10
    6:0.03
    7:0.02
    8:0.28
    9:0.13
    10:0.05
    11:0.03
    Negative Logits
    Statement
    -1.24
    cci
    -1.15
    SPONSORED
    -1.06
     coun
    -1.04
    cially
    -1.03
    TABLE
    -1.03
     tion
    -0.99
    KNOWN
    -0.97
    seq
    -0.97
    assadors
    -0.95
    POSITIVE LOGITS
     lid
    1.33
     eyeb
    1.25
    geist
    1.24
    inis
    1.08
     :(
    1.07
    erella
    1.06
     whistle
    1.05
    andel
    1.05
    emale
    1.05
     dirt
    1.04
    Activations Density 0.012%

    No Known Activations