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. 8333
    Prev
    Next
    INDEX
    Explanations

    references to images or slideshows related to events

    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
    1:0.20
    2:0.07
    3:0.08
    4:0.03
    5:0.02
    6:0.06
    7:0.10
    8:0.06
    9:0.16
    10:0.08
    11:0.08
    Negative Logits
     Archdemon
    -1.24
     Dictionary
    -1.15
    quote
    -1.13
     alike
    -1.12
    asions
    -1.11
     Dagger
    -1.10
    \-
    -1.08
    AIDS
    -1.07
    TABLE
    -1.07
     Parties
    -1.06
    POSITIVE LOGITS
    )</
    1.33
     skelet
    1.32
    ensation
    1.30
     curtain
    1.29
     Mehran
    1.28
     shutter
    1.23
    ').
    1.23
     disapp
    1.22
     suspic
    1.22
    emaker
    1.21
    Activations Density 0.002%

    No Known Activations