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. 8308
    Prev
    Next
    INDEX
    Explanations

    mentions of NASA and its affiliated centers and organizations

    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
    1:0.10
    2:0.07
    3:0.10
    4:0.04
    5:0.04
    6:0.10
    7:0.12
    8:0.08
    9:0.08
    10:0.09
    11:0.09
    Negative Logits
     Rite
    -1.16
    ammy
    -1.11
    agate
    -1.03
     despise
    -1.02
     Bleach
    -1.01
     Liqu
    -1.00
     voic
    -1.00
     stains
    -0.98
     drunk
    -0.98
     masse
    -0.97
    POSITIVE LOGITS
    ctic
    1.22
     Mellon
    1.16
    ESA
    1.10
     millenn
    1.07
     Scientific
    1.05
    NOW
    1.01
    Science
    0.99
    uclear
    0.99
    ECH
    0.98
    vell
    0.98
    Activations Density 0.022%

    No Known Activations