© 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. 2676
    Prev
    Next
    INDEX
    Explanations

    references to events and specific people or actions related to adaptation

    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
    1:0.02
    2:0.05
    3:0.04
    4:0.05
    5:0.02
    6:0.35
    7:0.04
    8:0.04
    9:0.21
    10:0.02
    11:0.04
    Negative Logits
     AUD
    -3.83
     Ez
    -3.78
    ��
    -3.73
    dar
    -3.61
     Razer
    -3.56
     GEAR
    -3.55
     Ember
    -3.53
     Gilmore
    -3.44
    handle
    -3.41
    DX
    -3.40
    POSITIVE LOGITS
    Pl
    8.20
     Pl
    7.66
    pl
    7.02
     PL
    6.99
     pl
    6.32
     Plat
    6.21
    PL
    6.03
     Plant
    5.49
     Plate
    5.16
     Platinum
    5.05
    Activations Density 0.020%

    No Known Activations