© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10268
    Prev
    Next
    INDEX
    Explanations

    specific codes or identifiers related to mod scripts and features in data

    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
    0:0.07
    1:0.10
    2:0.03
    3:0.06
    4:0.02
    5:0.05
    6:0.08
    7:0.03
    8:0.02
    9:0.42
    10:0.02
    11:0.05
    Negative Logits
     Gram
    -3.44
     Bord
    -3.36
     HIP
    -3.08
    Jackson
    -3.07
    houn
    -2.96
     partition
    -2.94
     cracked
    -2.92
     viol
    -2.83
     spons
    -2.81
    rien
    -2.80
    POSITIVE LOGITS
    00
    5.33
     00
    4.26
    004
    4.17
    002
    3.98
    008
    3.88
    003
    3.74
    005
    3.60
    0010
    3.60
    006
    3.57
     Nex
    3.42
    Activations Density 0.004%

    No Known Activations