© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 22929
    Prev
    Next
    INDEX
    Explanations

    references to specific companies, individuals, and their potential actions or outcomes in various contexts

    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
    0:0.03
    1:0.03
    2:0.08
    3:0.12
    4:0.03
    5:0.04
    6:0.03
    7:0.07
    8:0.03
    9:0.02
    10:0.45
    11:0.03
    Negative Logits
    ��
    -2.28
    tained
    -2.10
     amidst
    -1.97
    ciating
    -1.97
     amid
    -1.95
     lately
    -1.93
     during
    -1.92
    eger
    -1.92
     despite
    -1.82
    bilt
    -1.82
    POSITIVE LOGITS
    would
    3.68
     would
    3.39
     will
    3.21
    will
    3.17
     wouldn
    3.14
    might
    3.06
    could
    3.04
     should
    2.97
     might
    2.93
    should
    2.89
    Activations Density 0.538%

    No Known Activations