Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10347
    Prev
    Next
    INDEX
    Explanations

    regulatory terms and discussions related to compliance and oversight

    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
    0:0.03
    1:0.02
    2:0.07
    3:0.03
    4:0.03
    5:0.05
    6:0.22
    7:0.32
    8:0.06
    9:0.03
    10:0.06
    11:0.04
    Negative Logits
    animate
    -1.48
     expressive
    -1.14
     Sands
    -1.13
     appet
    -1.07
    sed
    -1.07
     sorcery
    -1.07
    below
    -1.02
    Kin
    -1.02
     resemblance
    -1.01
     Cub
    -1.00
    POSITIVE LOGITS
    merce
    1.40
    alion
    1.32
    hement
    1.31
     guid
    1.30
    arthed
    1.30
     Audit
    1.25
     accredited
    1.23
    ć
    1.21
     disbanded
    1.19
     publishes
    1.19
    Activations Density 0.190%

    No Known Activations