© 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. 45522
    Prev
    Next
    INDEX
    Explanations

    references to sources of information or authority figures in news reporting

    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
    0:0.02
    1:0.02
    2:0.08
    3:0.12
    4:0.32
    5:0.04
    6:0.06
    7:0.03
    8:0.04
    9:0.05
    10:0.09
    11:0.06
    Negative Logits
     "$:/
    -1.85
     undone
    -1.63
     Tradable
    -1.62
     hath
    -1.56
     shall
    -1.53
     disappears
    -1.53
     reverted
    -1.52
    ardless
    -1.52
     ceases
    -1.51
     destroys
    -1.51
    POSITIVE LOGITS
    alist
    1.64
    ographers
    1.48
    `.
    1.43
    verty
    1.42
     Cly
    1.41
     Lank
    1.40
     analysts
    1.40
    rc
    1.38
     Hanson
    1.38
    BIP
    1.37
    Activations Density 0.025%

    No Known Activations