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. 7880
    Prev
    Next
    INDEX
    Explanations

    phrases containing words related to guarantees and certainty

    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
    0:0.03
    1:0.02
    2:0.07
    3:0.23
    4:0.03
    5:0.02
    6:0.05
    7:0.16
    8:0.05
    9:0.10
    10:0.06
    11:0.11
    Negative Logits
    querade
    -1.35
    ESE
    -1.31
    itcher
    -1.31
    arse
    -1.28
    ////////////////
    -1.21
    ovie
    -1.20
    rosse
    -1.09
    bernatorial
    -1.08
    ////////////////////////////////
    -1.08
    edin
    -1.05
    POSITIVE LOGITS
     validity
    1.50
     perman
    1.46
     warranties
    1.42
    worthiness
    1.35
    ット
    1.30
     confidentiality
    1.29
     correctness
    1.26
     GPUs
    1.16
     rewards
    1.16
     fulfillment
    1.15
    Activations Density 0.009%

    No Known Activations