© 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. 13627
    Prev
    Next
    INDEX
    Explanations

    states of negation or negated actions

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.12
    1:0.03
    2:0.20
    3:0.10
    4:0.08
    5:0.06
    6:0.04
    7:0.02
    8:0.09
    9:0.08
    10:0.08
    11:0.04
    Negative Logits
     Vulkan
    -1.31
     Actions
    -1.12
    anwhile
    -1.11
    Package
    -1.10
    PHOTOS
    -1.07
    rants
    -1.07
     Tracker
    -1.07
    bytes
    -1.05
     Strategy
    -1.04
     lies
    -1.02
    POSITIVE LOGITS
    ukong
    1.68
    aign
    1.52
    ゼウス
    1.51
    ufficient
    1.41
    ossession
    1.40
    ividual
    1.38
    atown
    1.38
    obyl
    1.36
    estine
    1.35
    ilial
    1.33
    Activations Density 0.014%

    No Known Activations