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. 22449
    Prev
    Next
    INDEX
    Explanations

    phrases related to making sense or being meaningful

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

    phrases that express the concept of making a difference or sense

    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
    0:0.04
    1:0.01
    2:0.22
    3:0.08
    4:0.04
    5:0.05
    6:0.01
    7:0.06
    8:0.20
    9:0.06
    10:0.11
    11:0.06
    Negative Logits
    anwhile
    -1.11
     Pigs
    -1.03
    rought
    -1.00
    stration
    -0.97
    planes
    -0.97
    idth
    -0.95
     Boo
    -0.93
     initiated
    -0.93
     faithfully
    -0.92
     Badge
    -0.91
    POSITIVE LOGITS
    Wan
    1.49
    kish
    1.33
    �
    1.21
    undo
    1.20
    sense
    1.20
    ˈ
    1.19
     dent
    1.11
    _-_
    1.08
    Package
    1.07
    pmwiki
    1.07
    Activations Density 0.201%

    No Known Activations