© 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. 10-ATT-KK
    11. 14896
    Prev
    Next
    INDEX
    Explanations

    references to awards, honors, or recognitions

    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
    0:0.04
    1:0.12
    2:0.08
    3:0.12
    4:0.04
    5:0.03
    6:0.04
    7:0.08
    8:0.28
    9:0.04
    10:0.04
    11:0.05
    Negative Logits
    Joined
    -2.58
    Products
    -2.35
    ��
    -2.33
    abl
    -2.28
    atem
    -2.25
    ubi
    -2.19
    quit
    -2.09
    soDeliveryDate
    -2.07
     Palest
    -2.07
    yt
    -2.06
    POSITIVE LOGITS
     first
    6.42
     second
    6.41
    first
    5.71
    second
    5.22
     third
    4.87
     fourth
    4.82
    Second
    4.56
    First
    4.49
     First
    4.44
     FIRST
    4.44
    Activations Density 0.086%

    No Known Activations