© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43823
    Prev
    Next
    INDEX
    Explanations

    indications of rewards and benefits associated with various characters or titles in a narrative context

    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
    0:0.04
    1:0.01
    2:0.11
    3:0.10
    4:0.28
    5:0.03
    6:0.07
    7:0.08
    8:0.07
    9:0.04
    10:0.05
    11:0.06
    Negative Logits
    Led
    -1.60
    Engineers
    -1.55
    INO
    -1.52
    �
    -1.49
    mediated
    -1.38
    SPONSORED
    -1.36
    JUST
    -1.36
    sis
    -1.34
    ACTED
    -1.30
    IPS
    -1.30
    POSITIVE LOGITS
     goodies
    1.50
     thereto
    1.46
     probabilities
    1.43
     possibility
    1.40
     accrued
    1.33
     bacon
    1.32
     contacts
    1.32
     originals
    1.30
     fractions
    1.29
     tens
    1.28
    Activations Density 0.013%

    No Known Activations