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. 8531
    Prev
    Next
    INDEX
    Explanations

    references to reports and incidents involving health, safety, or crime

    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
    1:0.05
    2:0.16
    3:0.03
    4:0.03
    5:0.06
    6:0.07
    7:0.07
    8:0.23
    9:0.07
    10:0.07
    11:0.07
    Negative Logits
     ASA
    -1.39
    atcher
    -1.38
    ITED
    -1.37
     Sabha
    -1.35
    onga
    -1.29
     Suc
    -1.22
     Advocate
    -1.19
    ACTED
    -1.18
     outwe
    -1.18
    Reviewer
    -1.17
    POSITIVE LOGITS
     brilliance
    1.37
     gust
    1.22
     whims
    1.21
     sharks
    1.20
    tons
    1.20
     bodies
    1.19
     splend
    1.19
     precision
    1.17
     slogans
    1.15
     corpses
    1.15
    Activations Density 0.089%

    No Known Activations