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. 2-ATT-KK
    6. 22471
    Prev
    Next
    INDEX
    Explanations

    phrases related to the use of steam in various contexts, including technological processes and geothermal activity

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to sexual content in discussions or articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.03
    2:0.25
    3:0.05
    4:0.13
    5:0.06
    6:0.02
    7:0.02
    8:0.07
    9:0.19
    10:0.05
    11:0.02
    Negative Logits
     Triangle
    -1.52
    gdala
    -1.51
    ��
    -1.45
    VEN
    -1.28
    者
    -1.26
    querque
    -1.24
    MU
    -1.23
    �
    -1.23
    herty
    -1.22
     Crow
    -1.22
    POSITIVE LOGITS
    dating
    1.34
     oats
    1.29
     steam
    1.28
     load
    1.18
     peas
    1.18
    grading
    1.17
     flame
    1.14
     espresso
    1.14
     toilets
    1.14
     buggy
    1.13
    Activations Density 0.005%

    No Known Activations