© 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. 23314
    Prev
    Next
    INDEX
    Explanations

    traces of modifications, inconsistencies, or disruptions

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

    references to the impact of human actions and consequences

    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
    1:0.02
    2:0.04
    3:0.05
    4:0.03
    5:0.05
    6:0.03
    7:0.02
    8:0.50
    9:0.05
    10:0.06
    11:0.02
    Negative Logits
     Cosponsors
    -1.38
    wcsstore
    -1.35
    quickShipAvailable
    -1.29
     temperament
    -1.25
     coh
    -1.24
    utm
    -1.21
    iqueness
    -1.20
    FactoryReloaded
    -1.18
    FN
    -1.17
    ACTION
    -1.17
    POSITIVE LOGITS
     Islands
    1.54
     untouched
    1.44
     crater
    1.38
     intact
    1.34
     Ruk
    1.33
    asis
    1.33
     ashes
    1.33
     ash
    1.32
     charred
    1.30
     tidy
    1.29
    Activations Density 0.062%

    No Known Activations