© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43236
    Prev
    Next
    INDEX
    Explanations

    phrases related to user verification and validation processes

    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
    0:0.01
    1:0.01
    2:0.14
    3:0.12
    4:0.05
    5:0.02
    6:0.11
    7:0.28
    8:0.07
    9:0.04
    10:0.05
    11:0.03
    Negative Logits
    selage
    -1.90
    etus
    -1.81
    ////////////////////////////////
    -1.69
    viously
    -1.66
    ranged
    -1.66
    uries
    -1.65
    ipel
    -1.59
    ecycle
    -1.59
    ificantly
    -1.57
     Topics
    -1.56
    POSITIVE LOGITS
    RECT
    1.93
     CLSID
    1.67
     validity
    1.65
     verify
    1.64
     verification
    1.60
     approximation
    1.59
     PCR
    1.54
     waterproof
    1.52
     accuracy
    1.52
     password
    1.51
    Activations Density 0.002%

    No Known Activations