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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 19737
    Prev
    Next
    INDEX
    Explanations

    phrases that describe a sense of character or nature related to a specific subject or topic

    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
    1:0.02
    2:0.10
    3:0.04
    4:0.18
    5:0.03
    6:0.06
    7:0.32
    8:0.03
    9:0.03
    10:0.05
    11:0.08
    Negative Logits
    staking
    -1.60
    orthy
    -1.54
    occupied
    -1.47
    ears
    -1.46
    imposed
    -1.44
    raints
    -1.43
    geries
    -1.43
     leases
    -1.40
     waivers
    -1.40
    requ
    -1.39
    POSITIVE LOGITS
     Balanced
    1.54
     Tact
    1.53
     Courage
    1.46
     Tone
    1.41
     Sally
    1.40
     Diss
    1.39
     Culture
    1.36
     Ung
    1.36
     Mons
    1.32
    ��
    1.32
    Activations Density 0.002%

    No Known Activations