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. 22195
    Prev
    Next
    INDEX
    Explanations

    terms associated with reduction or trimming in various contexts

    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
    0:0.06
    1:0.03
    2:0.16
    3:0.08
    4:0.09
    5:0.05
    6:0.04
    7:0.03
    8:0.20
    9:0.12
    10:0.06
    11:0.03
    Negative Logits
     Administ
    -1.43
    iott
    -1.19
    SPONSORED
    -1.18
    assadors
    -1.16
     academia
    -1.11
    FA
    -1.11
    ukong
    -1.09
     Lamb
    -1.09
    WR
    -1.07
    Supported
    -1.06
    POSITIVE LOGITS
    ackets
    1.43
    acket
    1.32
    aughs
    1.27
     mustache
    1.21
     gland
    1.20
     notch
    1.18
     teeth
    1.13
    erous
    1.12
     tape
    1.11
    endas
    1.11
    Activations Density 0.002%

    No Known Activations