© 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. 46732
    Prev
    Next
    INDEX
    Explanations

    references to historical context and cultural critiques

    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
    0:0.03
    1:0.03
    2:0.07
    3:0.04
    4:0.07
    5:0.03
    6:0.37
    7:0.07
    8:0.03
    9:0.03
    10:0.10
    11:0.09
    Negative Logits
    emouth
    -1.77
    reau
    -1.68
    erella
    -1.56
    iflower
    -1.49
    enting
    -1.45
    endi
    -1.42
    itsch
    -1.42
    cht
    -1.41
    yip
    -1.40
    urry
    -1.39
    POSITIVE LOGITS
     sciences
    1.33
     finance
    1.30
     economics
    1.23
     Wonders
    1.21
     dispro
    1.21
     Tasmania
    1.19
     preservation
    1.18
     continuity
    1.17
     Judgment
    1.16
     alienation
    1.15
    Activations Density 0.011%

    No Known Activations