© 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. 17735
    Prev
    Next
    INDEX
    Explanations

    entries related to video links or online content references

    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
    1:0.01
    2:0.02
    3:0.11
    4:0.11
    5:0.09
    6:0.01
    7:0.29
    8:0.01
    9:0.02
    10:0.10
    11:0.03
    Negative Logits
     colle
    -2.54
    osph
    -2.23
    plin
    -2.08
    vre
    -2.06
    ngth
    -2.05
    Cache
    -2.04
     Vand
    -2.03
     challeng
    -1.98
     Hardy
    -1.98
     camoufl
    -1.97
    POSITIVE LOGITS
    imon
    2.45
    ope
    2.44
    Uk
    2.33
    &
    2.27
    ayne
    2.23
     Helpful
    2.22
    OY
    2.22
    enfranch
    2.21
    ohm
    2.19
     Anger
    2.17
    Activations Density 0.001%

    No Known Activations