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. 3-ATT-KK
    6. 8585
    Prev
    Next
    INDEX
    Explanations

    phrases indicating support or backing

    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
    0:0.02
    1:0.03
    2:0.09
    3:0.16
    4:0.02
    5:0.04
    6:0.07
    7:0.07
    8:0.08
    9:0.25
    10:0.07
    11:0.05
    Negative Logits
    Mass
    -1.34
    along
    -1.28
    iae
    -1.21
    hello
    -1.17
    sonian
    -1.16
    andowski
    -1.15
    bernatorial
    -1.11
    RN
    -1.10
    scl
    -1.10
    inse
    -1.10
    POSITIVE LOGITS
    enance
    1.43
     Sachs
    1.24
     corrupt
    1.15
     complicit
    1.15
     deceit
    1.14
     WTO
    1.12
     mislead
    1.10
     fraudulent
    1.09
     dishonest
    1.08
     Totem
    1.08
    Activations Density 0.007%

    No Known Activations