© 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. 42813
    Prev
    Next
    INDEX
    Explanations

    phrases that express truth or validity regarding a situation

    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
    1:0.01
    2:0.11
    3:0.08
    4:0.40
    5:0.06
    6:0.03
    7:0.10
    8:0.03
    9:0.04
    10:0.05
    11:0.04
    Negative Logits
    aily
    -1.78
    osponsors
    -1.76
    ossibility
    -1.57
    icter
    -1.56
    nown
    -1.55
    iscopal
    -1.55
    aughs
    -1.55
    DoS
    -1.53
    akespe
    -1.52
    cum
    -1.51
    POSITIVE LOGITS
     proceedings
    1.44
     psyche
    1.39
     doub
    1.39
     proceeding
    1.35
    ahime
    1.34
     Fei
    1.33
     equation
    1.30
     decisions
    1.28
     matters
    1.27
     Marriage
    1.27
    Activations Density 0.312%

    No Known Activations