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. 3-ATT-KK
    6. 7626
    Prev
    Next
    INDEX
    Explanations

    key phrases and dramatic events related to public controversies and celebrity actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.04
    2:0.15
    3:0.10
    4:0.01
    5:0.08
    6:0.10
    7:0.10
    8:0.10
    9:0.09
    10:0.08
    11:0.09
    Negative Logits
    ��
    -1.15
    �
    -1.03
    aza
    -1.01
    zynski
    -1.01
    ��
    -1.00
     Decay
    -0.96
     relying
    -0.93
     antioxid
    -0.88
    Magikarp
    -0.88
    iac
    -0.88
    POSITIVE LOGITS
    edin
    1.06
     microphone
    1.01
     his
    1.00
    ibus
    0.96
    auntlet
    0.95
    elo
    0.94
    inet
    0.93
    reply
    0.92
     bead
    0.91
     portrait
    0.89
    Activations Density 0.385%

    No Known Activations