© 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. 44573
    Prev
    Next
    INDEX
    Explanations

    discussions around political decisions and their implications

    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
    2:0.07
    3:0.41
    4:0.05
    5:0.03
    6:0.04
    7:0.03
    8:0.07
    9:0.05
    10:0.08
    11:0.08
    Negative Logits
    illac
    -1.57
    ukong
    -1.53
    UGH
    -1.51
    schild
    -1.51
    dullah
    -1.48
     MN
    -1.46
     NIGHT
    -1.43
    eele
    -1.42
     Nare
    -1.41
     Jonas
    -1.40
    POSITIVE LOGITS
     harmed
    1.72
     misinterpret
    1.63
    netflix
    1.58
     tram
    1.57
     "[
    1.54
     misled
    1.51
    Reloaded
    1.49
     unfairly
    1.47
     compromising
    1.46
    ��
    1.45
    Activations Density 0.289%

    No Known Activations