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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 19715
    Prev
    Next
    INDEX
    Explanations

    elements related to specific media, such as movies and music, along with their accompanying details like titles and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.05
    1:0.02
    2:0.09
    3:0.28
    4:0.09
    5:0.04
    6:0.02
    7:0.04
    8:0.04
    9:0.08
    10:0.09
    11:0.09
    Negative Logits
    soDeliveryDate
    -1.83
    ricane
    -1.80
    "))
    -1.80
    ItemThumbnailImage
    -1.67
    ":
    -1.66
    20439
    -1.66
     mosqu
    -1.66
    う
    -1.63
    "!
    -1.61
    rogram
    -1.57
    POSITIVE LOGITS
     (-
    1.64
     ($
    1.63
     [-
    1.57
    )</
    1.47
     [/
    1.41
     [+
    1.41
     reversible
    1.41
     rated
    1.40
     *)
    1.38
     ['
    1.36
    Activations Density 0.098%

    No Known Activations