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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 46264
    Prev
    Next
    INDEX
    Explanations

    prominent names of actors, particularly in the context of their roles and performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.01
    2:0.07
    3:0.14
    4:0.22
    5:0.03
    6:0.03
    7:0.08
    8:0.04
    9:0.05
    10:0.15
    11:0.08
    Negative Logits
     profitability
    -1.84
    gradation
    -1.67
     innovate
    -1.65
    achev
    -1.62
    iphate
    -1.59
    INESS
    -1.59
    coin
    -1.59
    matter
    -1.58
     replication
    -1.57
    evidence
    -1.56
    POSITIVE LOGITS
     TBA
    1.76
    *)
    1.75
     Leigh
    1.67
     Preston
    1.65
     Gale
    1.64
     Mum
    1.63
     Hels
    1.60
     Bil
    1.58
     Ake
    1.58
     Azerb
    1.58
    Activations Density 0.002%

    No Known Activations