© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 18867
    Prev
    Next
    INDEX
    Explanations

    instances of personal experiences or narratives involving significant events

    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
    0:0.07
    1:0.03
    2:0.05
    3:0.03
    4:0.05
    5:0.04
    6:0.25
    7:0.04
    8:0.06
    9:0.26
    10:0.03
    11:0.04
    Negative Logits
     Fiber
    -4.16
     Campbell
    -4.06
     Clicker
    -4.01
    ukemia
    -3.75
    FM
    -3.61
    FW
    -3.56
    anooga
    -3.53
     fiber
    -3.53
     Pupp
    -3.38
    fill
    -3.35
    POSITIVE LOGITS
     Raj
    9.31
     Rai
    4.30
     Taj
    4.30
     Vaj
    4.24
     Vers
    3.83
     Rahman
    3.83
     RC
    3.75
    aj
    3.67
     Shant
    3.67
    RAM
    3.66
    Activations Density 0.003%

    No Known Activations