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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14437
    Prev
    Next
    INDEX
    Explanations

    instances of numerical references or scores within context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.05
    2:0.05
    3:0.05
    4:0.05
    5:0.04
    6:0.09
    7:0.25
    8:0.04
    9:0.06
    10:0.09
    11:0.07
    Negative Logits
     Vanderbilt
    -2.81
     Silk
    -2.58
     Mariners
    -2.56
     Gazette
    -2.49
     solicitation
    -2.40
     Pathfinder
    -2.37
     Merlin
    -2.33
     hemp
    -2.32
     Ness
    -2.32
     Medina
    -2.32
    POSITIVE LOGITS
    psc
    2.69
    Palest
    2.27
     pic
    2.26
    picture
    2.26
    bet
    2.21
    hett
    2.20
    itar
    2.15
     rooft
    2.08
    nai
    2.08
    wake
    2.04
    Activations Density 0.000%

    No Known Activations