© 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 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. 9091
    Prev
    Next
    INDEX
    Explanations

    common conjunctions and phrases in the text

    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
    1:0.33
    2:0.04
    3:0.04
    4:0.03
    5:0.05
    6:0.13
    7:0.02
    8:0.02
    9:0.20
    10:0.03
    11:0.02
    Negative Logits
    trak
    -3.22
    soDeliveryDate
    -2.76
    andom
    -2.67
    ty
    -2.65
    ocated
    -2.63
    ansk
    -2.63
    tery
    -2.58
    astern
    -2.54
     Unique
    -2.51
    aji
    -2.49
    POSITIVE LOGITS
     well
    4.45
     wells
    4.21
     GOODMAN
    4.16
    well
    4.15
     Well
    4.03
     Wells
    3.55
    Well
    3.42
     solidly
    3.06
    oft
    3.00
     afore
    2.97
    Activations Density 0.003%

    No Known Activations