© 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. 13966
    Prev
    Next
    INDEX
    Explanations

    topics related to cinema and film industry metrics

    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
    1:0.03
    2:0.13
    3:0.06
    4:0.16
    5:0.22
    6:0.04
    7:0.04
    8:0.03
    9:0.11
    10:0.03
    11:0.05
    Negative Logits
    ";
    -3.26
    !".
    -3.20
     insofar
    -3.14
    …."
    -3.12
    ".
    -3.02
     anymore
    -2.94
    ?".
    -2.89
    .",
    -2.87
     [];
    -2.82
    …"
    -2.77
    POSITIVE LOGITS
     Photos
    3.98
     See
    3.45
    OTOS
    3.41
    Photos
    3.17
     Highlights
    3.17
     Releases
    3.15
     Send
    3.02
     Plays
    2.99
    Visit
    2.99
     Recap
    2.96
    Activations Density 0.002%

    No Known Activations