© 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. 33541
    Prev
    Next
    INDEX
    Explanations

    terms related to manipulating or influencing outcomes, particularly in a contextual or analytical discussion

    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
    1:0.01
    2:0.05
    3:0.06
    4:0.11
    5:0.02
    6:0.05
    7:0.42
    8:0.02
    9:0.03
    10:0.11
    11:0.05
    Negative Logits
    olid
    -1.62
    ervative
    -1.56
    amaz
    -1.55
    ulf
    -1.53
    spring
    -1.52
    quer
    -1.52
     swear
    -1.52
    netflix
    -1.51
    bang
    -1.46
    inis
    -1.44
    POSITIVE LOGITS
     Niet
    1.61
     tickets
    1.55
     numer
    1.54
     weaknesses
    1.54
     IQ
    1.53
     difficulties
    1.49
    sided
    1.47
     durability
    1.45
     affordability
    1.43
     perceptions
    1.43
    Activations Density 0.001%

    No Known Activations