© 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. 10204
    Prev
    Next
    INDEX
    Explanations

    phrases related to partnerships or collaborative agreements

    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
    0:0.05
    1:0.05
    2:0.04
    3:0.09
    4:0.39
    5:0.06
    6:0.06
    7:0.04
    8:0.03
    9:0.06
    10:0.03
    11:0.04
    Negative Logits
     dstg
    -2.54
    LOD
    -2.53
    Numbers
    -2.49
    ctors
    -2.23
    Weapons
    -2.17
    Events
    -2.13
     acron
    -2.13
     teasp
    -2.12
    REC
    -2.08
     approvals
    -2.07
    POSITIVE LOGITS
     a
    3.26
     an
    2.96
    a
    2.88
    \":
    2.76
    pires
    2.72
    ndum
    2.63
     hypothetical
    2.58
     afore
    2.54
    A
    2.51
     A
    2.47
    Activations Density 0.504%

    No Known Activations