© 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. 3-ATT-KK
    6. 8178
    Prev
    Next
    INDEX
    Explanations

    negative or problematic states and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    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
    2:0.15
    3:0.14
    4:0.01
    5:0.03
    6:0.10
    7:0.08
    8:0.09
    9:0.18
    10:0.08
    11:0.03
    Negative Logits
     entrance
    -1.11
     backdrop
    -1.09
    INO
    -1.08
    Pokémon
    -1.04
    ection
    -1.02
    Bound
    -0.98
     Latter
    -0.94
    TP
    -0.94
    CHAT
    -0.93
    RECT
    -0.93
    POSITIVE LOGITS
     unnoticed
    1.31
     lately
    1.14
    ener
    1.11
    oslav
    1.10
     miser
    1.09
    enium
    1.04
     overboard
    1.04
    sterdam
    1.02
    govtrack
    1.01
    ocally
    1.01
    Activations Density 0.009%

    No Known Activations