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. 8344
    Prev
    Next
    INDEX
    Explanations

    phrases indicating benefits or gains

    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
    0:0.01
    1:0.02
    2:0.13
    3:0.19
    4:0.01
    5:0.02
    6:0.05
    7:0.08
    8:0.06
    9:0.22
    10:0.06
    11:0.08
    Negative Logits
    soDeliveryDate
    -1.75
    ulhu
    -1.24
     ILCS
    -1.14
    aft
    -1.10
    soType
    -1.10
    ISS
    -1.10
    acion
    -1.09
    DragonMagazine
    -1.07
    atl
    -1.07
    Temperature
    -1.06
    POSITIVE LOGITS
     digestion
    1.47
     greatly
    1.29
     outweigh
    1.21
    anke
    1.21
     tremend
    1.19
     Become
    1.13
     enormously
    1.10
     sensibilities
    1.09
     tremendously
    1.09
     compens
    1.03
    Activations Density 0.011%

    No Known Activations