© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 35644
    Prev
    Next
    INDEX
    Explanations

    cross-border references and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.03
    2:0.07
    3:0.06
    4:0.05
    5:0.04
    6:0.36
    7:0.08
    8:0.05
    9:0.05
    10:0.05
    11:0.08
    Negative Logits
    PDATE
    -1.29
     srfAttach
    -1.27
    Lago
    -1.27
     Likes
    -1.26
     Hits
    -1.15
     Happ
    -1.15
    LI
    -1.15
    zee
    -1.14
     flashbacks
    -1.11
    ICAN
    -1.11
    POSITIVE LOGITS
    perse
    1.73
    cipline
    1.66
    arching
    1.63
    rency
    1.43
    imeters
    1.29
    lining
    1.27
    sheet
    1.26
    backer
    1.26
    sheets
    1.24
    utor
    1.22
    Activations Density 0.007%

    No Known Activations