© 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. 28500
    Prev
    Next
    INDEX
    Explanations

    structures indicating subtraction or comparisons in complex scenarios

    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
    0:0.03
    1:0.02
    2:0.06
    3:0.09
    4:0.11
    5:0.03
    6:0.04
    7:0.37
    8:0.04
    9:0.04
    10:0.06
    11:0.07
    Negative Logits
    beit
    -1.64
    AIR
    -1.58
    standing
    -1.52
    ANS
    -1.52
    Statement
    -1.52
    Demand
    -1.50
    Led
    -1.49
    VIDEO
    -1.48
    ================================================================
    -1.43
    eer
    -1.42
    POSITIVE LOGITS
     Vie
    1.59
     subtract
    1.50
     supplement
    1.43
     recomp
    1.42
    pell
    1.37
     Gil
    1.37
     Simpl
    1.34
     ($
    1.34
     (-
    1.34
     Frequency
    1.33
    Activations Density 0.000%

    No Known Activations