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. 8610
    Prev
    Next
    INDEX
    Explanations

    references to notable events, particularly related to specific individuals' actions and timelines

    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
    1:0.07
    2:0.08
    3:0.02
    4:0.02
    5:0.05
    6:0.06
    7:0.04
    8:0.11
    9:0.10
    10:0.08
    11:0.30
    Negative Logits
    erate
    -1.38
     Supporting
    -1.31
    Topics
    -1.21
     FEMA
    -1.14
     Volunteers
    -1.12
     slideshow
    -1.10
    Recommend
    -1.08
    soever
    -1.06
    IU
    -1.06
     Included
    -1.05
    POSITIVE LOGITS
    acqu
    1.39
    holiday
    1.22
    actionDate
    1.18
     recess
    1.18
     franch
    1.16
     prints
    1.15
    weapons
    1.14
     expired
    1.13
     acqu
    1.12
     disbanded
    1.12
    Activations Density 0.080%

    No Known Activations