© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 47179
    Prev
    Next
    INDEX
    Explanations

    topics related to addressing and resolving various issues or problems

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.07
    3:0.07
    4:0.20
    5:0.02
    6:0.03
    7:0.31
    8:0.02
    9:0.03
    10:0.07
    11:0.08
    Negative Logits
     announ
    -1.53
    DragonMagazine
    -1.51
     announcer
    -1.48
     endors
    -1.46
    hover
    -1.38
     accompanying
    -1.35
     cheered
    -1.34
     assurances
    -1.33
    friends
    -1.32
    oscope
    -1.28
    POSITIVE LOGITS
     uphill
    1.84
    problem
    1.68
     thorn
    1.63
     turf
    1.62
     deficit
    1.60
     brick
    1.56
     taboo
    1.53
     Question
    1.50
     problem
    1.49
    vable
    1.48
    Activations Density 0.005%

    No Known Activations