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. 11084
    Prev
    Next
    INDEX
    Explanations

    guidelines and safe practices related to personal safety and well-being

    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
    0:0.04
    1:0.06
    2:0.10
    3:0.07
    4:0.25
    5:0.05
    6:0.04
    7:0.13
    8:0.03
    9:0.03
    10:0.07
    11:0.08
    Negative Logits
    lished
    -2.28
     alleged
    -2.22
     clashed
    -2.22
     purported
    -2.22
    arser
    -2.18
     disputed
    -2.18
    ificantly
    -2.16
    urtle
    -2.13
     halted
    -2.09
     allegedly
    -2.09
    POSITIVE LOGITS
     Your
    5.02
    Your
    4.98
    your
    4.73
    You
    4.18
     You
    4.08
     your
    3.90
    Remember
    3.84
     Choose
    3.77
     Remember
    3.75
     Ideally
    3.73
    Activations Density 0.514%

    No Known Activations