© 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. 10-ATT-KK
    11. 8358
    Prev
    Next
    INDEX
    Explanations

    topics related to economic and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.03
    2:0.04
    3:0.12
    4:0.16
    5:0.15
    6:0.03
    7:0.06
    8:0.06
    9:0.10
    10:0.05
    11:0.09
    Negative Logits
     …
    -4.69
     ­
    -4.27
    ….
    -4.12
    …
    -3.95
    ……
    -3.79
     …"
    -3.78
    …)
    -3.61
     […]
    -3.60
    …..
    -3.54
    …."
    -3.54
    POSITIVE LOGITS
    Adds
    2.65
    ----------
    2.63
     Fixes
    2.60
    :-
    2.59
    -+-+
    2.58
    needs
    2.45
    Quality
    2.36
     -
    2.31
    -----------
    2.31
     "-
    2.30
    Activations Density 0.074%

    No Known Activations