© 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. 9-ATT-KK
    6. 3313
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.04
    2:0.07
    3:0.06
    4:0.06
    5:0.05
    6:0.20
    7:0.06
    8:0.07
    9:0.19
    10:0.04
    11:0.05
    Negative Logits
     Phill
    -3.53
    Sel
    -3.51
    ERC
    -3.40
     CLA
    -3.36
     Sel
    -3.31
    arine
    -3.17
     HS
    -3.13
     ste
    -3.11
    ranch
    -3.03
     CC
    -3.01
    POSITIVE LOGITS
     Doom
    8.64
     Boom
    7.59
    oom
    6.00
     doom
    5.31
     boom
    4.59
     Zoom
    4.14
     Mania
    4.13
     Quake
    4.13
     Bam
    4.00
     bom
    3.97
    Activations Density 0.001%

    No Known Activations