© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 12534
    Prev
    Next
    INDEX
    Explanations

    words related to unexpected or unusual occurrences or characteristics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases indicating states of being and opinions expressed about events or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.07
    2:0.07
    3:0.03
    4:0.02
    5:0.08
    6:0.05
    7:0.04
    8:0.11
    9:0.34
    10:0.07
    11:0.06
    Negative Logits
    adra
    -1.60
    rons
    -1.44
    oop
    -1.42
    interstitial
    -1.36
     deposition
    -1.35
    APD
    -1.33
    ogan
    -1.32
    Stretch
    -1.32
    mouth
    -1.31
    lict
    -1.26
    POSITIVE LOGITS
     miscon
    1.61
     underest
    1.52
     achievable
    1.44
     impossibility
    1.37
     positives
    1.36
     beforehand
    1.32
     preferable
    1.30
     bluff
    1.25
     overest
    1.25
     IPA
    1.25
    Activations Density 0.051%

    No Known Activations