© 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. 12210
    Prev
    Next
    INDEX
    Explanations

    names of songs and places related to a musical context

    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
    0:0.03
    1:0.52
    2:0.03
    3:0.03
    4:0.02
    5:0.06
    6:0.06
    7:0.04
    8:0.02
    9:0.08
    10:0.02
    11:0.05
    Negative Logits
    esters
    -2.56
     1972
    -2.41
    uble
    -2.41
     heck
    -2.24
    assian
    -2.24
    sworth
    -2.22
    acket
    -2.21
    ault
    -2.20
    BIT
    -2.18
    472
    -2.16
    POSITIVE LOGITS
    10
    3.96
     10
    3.82
     tenth
    3.62
    9
    3.58
     ninth
    3.44
    11
    3.41
     9
    3.34
     11
    3.19
     999
    3.12
    999
    2.97
    Activations Density 0.041%

    No Known Activations