© 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. 5-ATT-KK
    11. 27851
    Prev
    Next
    INDEX
    Explanations

    instances of comparative language or contrasts between different ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    1:0.01
    2:0.35
    3:0.10
    4:0.11
    5:0.03
    6:0.03
    7:0.05
    8:0.06
    9:0.05
    10:0.07
    11:0.08
    Negative Logits
    grown
    -1.64
    ..........
    -1.50
    elaide
    -1.48
    ortium
    -1.44
     valued
    -1.40
     handcuffs
    -1.34
     nationwide
    -1.34
    Fra
    -1.34
    ideon
    -1.32
     convertible
    -1.27
    POSITIVE LOGITS
    Interstitial
    1.84
    ◼
    1.74
     Negative
    1.64
     Behavioral
    1.58
    rw
    1.56
     ⓘ
    1.56
     Occupations
    1.53
    rone
    1.44
    ignty
    1.42
     Modes
    1.42
    Activations Density 0.060%

    No Known Activations