© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 21784
    Prev
    Next
    INDEX
    Explanations

    references to production and artistic studios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.06
    2:0.16
    3:0.05
    4:0.05
    5:0.10
    6:0.03
    7:0.04
    8:0.05
    9:0.28
    10:0.06
    11:0.03
    Negative Logits
    ividual
    -1.48
    maxwell
    -1.32
     amnesty
    -1.30
     aven
    -1.30
    jiang
    -1.29
     scram
    -1.23
    ndra
    -1.22
     scourge
    -1.22
    ullah
    -1.19
    andering
    -1.17
    POSITIVE LOGITS
    Studio
    1.53
    iHUD
    1.46
     studios
    1.45
    Dialogue
    1.36
    interstitial
    1.35
     Indie
    1.32
     Artists
    1.28
     Rooms
    1.27
    tracks
    1.21
     Fell
    1.21
    Activations Density 0.021%

    No Known Activations