© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 20478
    Prev
    Next
    INDEX
    Explanations

    references to publication or documentation processes

    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
    0:0.09
    1:0.12
    2:0.17
    3:0.05
    4:0.02
    5:0.04
    6:0.11
    7:0.03
    8:0.03
    9:0.22
    10:0.03
    11:0.03
    Negative Logits
     Mell
    -3.52
     Pell
    -3.25
    ells
    -3.10
     Daly
    -3.09
     Ellis
    -2.97
    plex
    -2.94
     sd
    -2.89
     resin
    -2.83
     Aires
    -2.80
     Gross
    -2.79
    POSITIVE LOGITS
    follow
    6.16
     followed
    5.25
     follow
    5.15
     Follow
    4.97
     follower
    4.41
    ollower
    4.32
    Follow
    4.30
     follows
    3.80
     preced
    3.76
     followers
    3.69
    Activations Density 0.010%

    No Known Activations