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. 8470
    Prev
    Next
    INDEX
    Explanations

    words related to financial constraints and challenges

    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
    0:0.04
    1:0.02
    2:0.06
    3:0.09
    4:0.03
    5:0.04
    6:0.08
    7:0.11
    8:0.04
    9:0.06
    10:0.10
    11:0.27
    Negative Logits
    Balt
    -1.20
     Koran
    -1.18
     empowerment
    -1.13
    ACTED
    -1.13
     Correct
    -1.03
    yrics
    -0.98
    voice
    -0.97
    appropriately
    -0.97
    DragonMagazine
    -0.97
     reflections
    -0.96
    POSITIVE LOGITS
     (>
    1.43
     rush
    1.26
     onslaught
    1.22
     exceeded
    1.20
     surpassed
    1.18
     existed
    1.14
     ever
    1.14
    ��
    1.12
     exceed
    1.10
    gling
    1.10
    Activations Density 0.002%

    No Known Activations