© 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. 14931
    Prev
    Next
    INDEX
    Explanations

    details related to user profile information

    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
    0:0.13
    1:0.02
    2:0.02
    3:0.09
    4:0.16
    5:0.16
    6:0.06
    7:0.13
    8:0.02
    9:0.03
    10:0.10
    11:0.03
    Negative Logits
    ichever
    -2.45
    ngth
    -2.24
    elman
    -2.15
    ancies
    -1.91
    annis
    -1.90
     Netflix
    -1.90
     ambitions
    -1.89
     improv
    -1.89
    Netflix
    -1.87
    enture
    -1.82
    POSITIVE LOGITS
    Joined
    3.00
    Thread
    2.82
    Quote
    2.15
     thread
    2.11
     Member
    2.11
    Member
    2.08
    quote
    2.06
     Quote
    2.06
    assembly
    2.05
    Pin
    2.04
    Activations Density 0.003%

    No Known Activations