© 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. 2-ATT-KK
    6. 22999
    Prev
    Next
    INDEX
    Explanations

    organizations, institutions, and specific individuals involved in various political, social, legal, and international affairs

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

    references to organizations and initiatives related to human rights and social justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.03
    2:0.13
    3:0.08
    4:0.08
    5:0.12
    6:0.04
    7:0.02
    8:0.12
    9:0.13
    10:0.10
    11:0.03
    Negative Logits
    nown
    -1.52
    fen
    -1.26
     tho
    -1.23
     sidew
    -1.21
     fools
    -1.20
     yours
    -1.19
     rand
    -1.19
     toget
    -1.18
    oresc
    -1.18
     fitt
    -1.18
    POSITIVE LOGITS
    ummies
    1.69
     Prevention
    1.58
    SPONSORED
    1.56
     Reconstruction
    1.50
     Anthropology
    1.48
     purposes
    1.42
    Gender
    1.42
     Sanctuary
    1.41
     Studies
    1.40
     Politics
    1.37
    Activations Density 0.134%

    No Known Activations