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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10431
    Prev
    Next
    INDEX
    Explanations

    mentions of the CIA and related intelligence activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.03
    2:0.06
    3:0.07
    4:0.03
    5:0.05
    6:0.24
    7:0.19
    8:0.04
    9:0.04
    10:0.09
    11:0.06
    Negative Logits
     candles
    -1.12
    phabet
    -1.10
    sing
    -1.10
    below
    -1.10
    iq
    -1.08
    lis
    -1.06
    hani
    -1.04
    oppers
    -1.02
    Kin
    -1.01
    liga
    -1.01
    POSITIVE LOGITS
    ionage
    1.09
     civilian
    1.09
     Secret
    1.08
     advisers
    1.08
    uminati
    1.06
     covert
    1.05
     Malf
    1.04
     wiret
    1.04
     bribes
    1.03
     secretaries
    1.03
    Activations Density 0.014%

    No Known Activations