Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 18678
    Prev
    Next
    INDEX
    Explanations

    key numerical values and identifiers in data

    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
    0:0.05
    1:0.03
    2:0.02
    3:0.08
    4:0.03
    5:0.02
    6:0.42
    7:0.02
    8:0.03
    9:0.20
    10:0.03
    11:0.02
    Negative Logits
     Monarch
    -3.83
     MAS
    -3.59
     Slave
    -3.52
     Marriage
    -3.48
    Rub
    -3.46
     Row
    -3.34
     Rut
    -3.23
     Liberty
    -3.22
     Lyn
    -3.20
     Kingdom
    -3.19
    POSITIVE LOGITS
    adi
    4.58
    alli
    4.37
    chi
    4.25
    oi
    4.06
    uri
    4.05
    soType
    4.00
    anni
    3.94
    ori
    3.93
    atti
    3.82
    ugi
    3.81
    Activations Density 0.035%

    No Known Activations