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. 8355
    Prev
    Next
    INDEX
    Explanations

    links and references to external content

    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
    1:0.02
    2:0.08
    3:0.25
    4:0.01
    5:0.04
    6:0.05
    7:0.12
    8:0.05
    9:0.17
    10:0.08
    11:0.06
    Negative Logits
    sych
    -1.25
    ificial
    -1.22
    ‎
    -1.22
    FACE
    -1.21
    dose
    -1.21
    aqu
    -1.20
    BUG
    -1.19
    dain
    -1.18
    dq
    -1.18
    given
    -1.18
    POSITIVE LOGITS
     dots
    1.69
     referral
    1.34
     links
    1.31
     webpage
    1.21
     compilation
    1.17
     Links
    1.16
     keywords
    1.16
     iceberg
    1.15
     URLs
    1.14
     websites
    1.13
    Activations Density 0.016%

    No Known Activations