© 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. 5-ATT-KK
    11. 44154
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.09
    2:0.07
    3:0.07
    4:0.07
    5:0.07
    6:0.08
    7:0.06
    8:0.06
    9:0.13
    10:0.09
    11:0.07
    Negative Logits
    nuclear
    -1.72
     loyal
    -1.64
     universes
    -1.64
    debian
    -1.60
    uclear
    -1.55
    usercontent
    -1.45
     wasteland
    -1.42
    ��
    -1.42
    Sorry
    -1.40
    姫
    -1.39
    POSITIVE LOGITS
    sterdam
    1.69
    adem
    1.67
    itiz
    1.55
     immersion
    1.43
    apy
    1.43
    alez
    1.40
     tray
    1.40
    imester
    1.40
    iry
    1.40
    ��
    1.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.