© 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. 9-ATT-KK
    11. 10549
    Prev
    Next
    INDEX
    Explanations

    conditional statements related to programming loops and their management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.05
    2:0.10
    3:0.04
    4:0.04
    5:0.03
    6:0.19
    7:0.04
    8:0.05
    9:0.20
    10:0.04
    11:0.05
    Negative Logits
    cit
    -4.09
     Sorce
    -3.84
    ettlement
    -3.76
    PET
    -3.76
    Naz
    -3.60
     Sed
    -3.55
     cit
    -3.48
    gender
    -3.46
     Petersen
    -3.44
    Pitt
    -3.41
    POSITIVE LOGITS
     loops
    8.74
     Loop
    8.72
     loop
    8.66
    Loop
    7.96
    loop
    7.86
     Lo
    4.77
     Hook
    4.73
    Lo
    4.15
     hooks
    3.98
     hook
    3.85
    Activations Density 0.006%

    No Known Activations