© 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. 18404
    Prev
    Next
    INDEX
    Explanations

    sentences containing expressions of opinion or commentary on a subject

    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
    0:0.07
    1:0.05
    2:0.06
    3:0.06
    4:0.06
    5:0.05
    6:0.21
    7:0.05
    8:0.08
    9:0.16
    10:0.05
    11:0.05
    Negative Logits
    Marsh
    -3.49
    Indian
    -3.21
     Burton
    -3.20
     Marshall
    -3.19
     Mans
    -3.19
     McInt
    -3.18
     Ulster
    -3.18
    CF
    -3.17
     TY
    -3.15
     CF
    -3.12
    POSITIVE LOGITS
     Orb
    7.64
     orb
    6.55
     Borg
    6.00
     orbs
    5.58
     org
    5.51
    orb
    5.04
     Asgard
    4.24
     orgasm
    4.10
     Artemis
    4.03
    ████
    3.92
    Activations Density 0.001%

    No Known Activations