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. 5-ATT-KK
    6. 44454
    Prev
    Next
    INDEX
    Explanations

    various forms of media manipulation and propaganda, particularly relating to political influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.08
    3:0.05
    4:0.05
    5:0.03
    6:0.07
    7:0.09
    8:0.03
    9:0.04
    10:0.32
    11:0.16
    Negative Logits
    bernatorial
    -1.48
    inventoryQuantity
    -1.35
     nominate
    -1.21
    zie
    -1.20
    �
    -1.19
    otide
    -1.18
     strugg
    -1.18
    joice
    -1.17
    angan
    -1.17
     contrace
    -1.16
    POSITIVE LOGITS
     infiltration
    1.52
     propaganda
    1.36
    present
    1.23
     disinformation
    1.22
    occ
    1.22
     cloaked
    1.21
     disgu
    1.21
     camoufl
    1.21
     presence
    1.20
    advertising
    1.17
    Activations Density 0.010%

    No Known Activations