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. 8539
    Prev
    Next
    INDEX
    Explanations

    words related to freedom and its limitations

    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
    1:0.02
    2:0.06
    3:0.37
    4:0.01
    5:0.01
    6:0.10
    7:0.07
    8:0.03
    9:0.05
    10:0.07
    11:0.13
    Negative Logits
    ��
    -1.42
    ashtra
    -1.41
    ��
    -1.36
    TPS
    -1.33
    ��
    -1.32
    nai
    -1.26
     unfocusedRange
    -1.24
    oyal
    -1.20
    artisan
    -1.18
    �
    -1.17
    POSITIVE LOGITS
     exerc
    1.39
    ercise
    1.30
     improv
    1.28
     exercise
    1.27
    Initialized
    1.27
     respawn
    1.27
     breat
    1.22
     improvis
    1.22
     bets
    1.22
     surprises
    1.21
    Activations Density 0.035%

    No Known Activations