© 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. 38014
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue and speech patterns within the text

    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
    0:0.06
    1:0.03
    2:0.06
    3:0.13
    4:0.05
    5:0.05
    6:0.07
    7:0.09
    8:0.05
    9:0.06
    10:0.16
    11:0.15
    Negative Logits
     dominates
    -1.58
     predomin
    -1.57
     enforcement
    -1.57
     nets
    -1.56
     tailored
    -1.56
     deterrent
    -1.56
     influ
    -1.53
     enforced
    -1.52
     enforce
    -1.51
     controvers
    -1.50
    POSITIVE LOGITS
    Fuck
    1.67
    ./
    1.65
     Empty
    1.63
    ..."
    1.61
     Thinking
    1.59
     Congratulations
    1.59
     Bastard
    1.57
    laughs
    1.56
    Finish
    1.55
    ?",
    1.54
    Activations Density 0.004%

    No Known Activations