© 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. 10530
    Prev
    Next
    INDEX
    Explanations

    instances of editorial roles and announcements in the context of media or news

    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
    0:0.34
    1:0.02
    2:0.13
    3:0.08
    4:0.03
    5:0.08
    6:0.04
    7:0.04
    8:0.06
    9:0.07
    10:0.03
    11:0.03
    Negative Logits
    ramid
    -3.06
    ��
    -3.04
     Qualcomm
    -3.03
     induct
    -2.92
    ��
    -2.68
     antennas
    -2.62
     halftime
    -2.56
     Cricket
    -2.55
     worship
    -2.50
     pav
    -2.48
    POSITIVE LOGITS
     editors
    6.31
     editing
    5.91
     editor
    5.85
     Editors
    5.36
    editor
    5.30
     Editing
    5.25
     edits
    5.22
     edit
    5.05
     Editor
    5.04
     edited
    4.84
    Activations Density 0.042%

    No Known Activations