© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 14871
    Prev
    Next
    INDEX
    Explanations

    quantifiable data and statistics, particularly regarding financial figures and organizational details

    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
    0:0.04
    1:0.14
    2:0.02
    3:0.04
    4:0.03
    5:0.03
    6:0.09
    7:0.03
    8:0.03
    9:0.44
    10:0.03
    11:0.03
    Negative Logits
     Royale
    -3.48
    gres
    -3.30
     AWS
    -3.18
     Tok
    -3.14
     Vac
    -3.13
    qv
    -3.13
    esta
    -3.08
     digest
    -3.07
    hof
    -2.98
     Slime
    -2.97
    POSITIVE LOGITS
     38
    5.42
    38
    5.22
     37
    4.65
    37
    4.62
     1937
    4.44
     Mim
    4.44
     376
    4.38
     1938
    4.26
     36
    4.17
    36
    4.06
    Activations Density 0.008%

    No Known Activations