© 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. 10-ATT-KK
    6. 14199
    Prev
    Next
    INDEX
    Explanations

    references to organizations and their legal or operational documents

    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
    0:0.02
    1:0.02
    2:0.03
    3:0.04
    4:0.10
    5:0.37
    6:0.03
    7:0.03
    8:0.01
    9:0.24
    10:0.02
    11:0.03
    Negative Logits
    DragonMagazine
    -3.14
    natureconservancy
    -2.86
     kindred
    -2.77
     Seym
    -2.70
    ngth
    -2.58
    arching
    -2.52
    soDeliveryDate
    -2.48
    uggle
    -2.41
    PsyNetMessage
    -2.40
     placebo
    -2.40
    POSITIVE LOGITS
     describes
    5.03
     reads
    4.92
     warns
    4.91
     specifies
    4.85
     mentions
    4.83
     advises
    4.72
     declares
    4.70
     stated
    4.63
     asserts
    4.58
     indicates
    4.53
    Activations Density 0.380%

    No Known Activations