© 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. 44533
    Prev
    Next
    INDEX
    Explanations

    references to expectations, assessments, and demands related to products or situations

    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
    0:0.02
    1:0.01
    2:0.20
    3:0.12
    4:0.23
    5:0.05
    6:0.04
    7:0.09
    8:0.07
    9:0.04
    10:0.04
    11:0.05
    Negative Logits
    icent
    -1.58
     VIDE
    -1.48
    onding
    -1.48
     Participation
    -1.46
    emonic
    -1.40
    ="/
    -1.40
    artifacts
    -1.40
     vs
    -1.36
    inational
    -1.36
     Quit
    -1.35
    POSITIVE LOGITS
     Gand
    1.36
     Bir
    1.30
     predicted
    1.22
     Rack
    1.22
     Brach
    1.22
     envisioned
    1.18
     figured
    1.18
     anticipated
    1.16
    got
    1.16
    Fan
    1.16
    Activations Density 0.020%

    No Known Activations