© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43123
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating reliability and fun in various contexts

    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
    0:0.01
    1:0.02
    2:0.05
    3:0.03
    4:0.05
    5:0.03
    6:0.45
    7:0.09
    8:0.03
    9:0.03
    10:0.10
    11:0.05
    Negative Logits
    sbm
    -1.35
    �醒
    -1.27
     omission
    -1.27
    版
    -1.25
    pecially
    -1.25
    Products
    -1.25
    displayText
    -1.24
    Items
    -1.23
     mortg
    -1.22
     parcels
    -1.21
    POSITIVE LOGITS
    ounters
    1.63
    ivism
    1.32
    bury
    1.31
     Furious
    1.30
    oling
    1.29
    reflect
    1.29
    idation
    1.25
    rieg
    1.24
    fusc
    1.23
    helm
    1.23
    Activations Density 0.011%

    No Known Activations