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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 22319
    Prev
    Next
    INDEX
    Explanations

    key terms associated with legal issues and societal structures

    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
    0:0.07
    1:0.04
    2:0.12
    3:0.10
    4:0.04
    5:0.16
    6:0.05
    7:0.02
    8:0.13
    9:0.10
    10:0.09
    11:0.04
    Negative Logits
    BuyableInstoreAndOnline
    -1.19
    ipel
    -1.10
    ecycle
    -1.08
    OUT
    -1.07
    arters
    -1.06
    bilt
    -1.05
    akedown
    -1.04
    icho
    -1.04
    ategory
    -1.04
    IFT
    -1.03
    POSITIVE LOGITS
     persisted
    1.20
     couldn
    1.17
     cannot
    1.16
     persists
    1.13
     mattered
    1.12
     depended
    1.12
     existed
    1.08
     lacks
    1.06
     disappeared
    1.06
     lacked
    1.05
    Activations Density 0.133%

    No Known Activations