© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 4748
    Prev
    Next
    INDEX
    Explanations

    references to ineffective efforts and criticisms of political actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    1:0.00
    2:0.30
    3:0.08
    4:0.07
    5:0.02
    6:0.03
    7:0.04
    8:0.04
    9:0.04
    10:0.22
    11:0.08
    Negative Logits
    iri
    -1.61
     herself
    -1.58
     Likes
    -1.56
     Antar
    -1.55
    thood
    -1.55
     Argent
    -1.55
    aurus
    -1.51
     Alz
    -1.49
     Superior
    -1.47
     Serving
    -1.47
    POSITIVE LOGITS
    FML
    2.12
     misguided
    1.83
    TPS
    1.79
    catentry
    1.79
    oldown
    1.76
     attempts
    1.76
    natureconservancy
    1.74
     unsuccessful
    1.72
     muted
    1.71
    Attempts
    1.68
    Activations Density 0.043%

    No Known Activations