© 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. 9258
    Prev
    Next
    INDEX
    Explanations

    specific dates and educational institutions

    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
    1:0.25
    2:0.03
    3:0.06
    4:0.03
    5:0.05
    6:0.08
    7:0.06
    8:0.02
    9:0.19
    10:0.03
    11:0.12
    Negative Logits
     Kappa
    -2.83
     amplified
    -2.69
     Replay
    -2.60
     Primal
    -2.59
     targ
    -2.51
    Push
    -2.49
    hai
    -2.48
    =]
    -2.46
     ($)
    -2.45
    agent
    -2.44
    POSITIVE LOGITS
    icut
    3.48
     Hallow
    3.07
    suff
    2.81
    cellaneous
    2.73
    ouf
    2.70
    committee
    2.68
     mattress
    2.57
    nec
    2.50
    foundation
    2.44
     istg
    2.39
    Activations Density 0.000%

    No Known Activations