Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11150
    Prev
    Next
    INDEX
    Explanations

    references to game-related terms and scoring metrics

    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
    0:0.02
    1:0.10
    2:0.03
    3:0.04
    4:0.03
    5:0.04
    6:0.05
    7:0.04
    8:0.02
    9:0.54
    10:0.02
    11:0.02
    Negative Logits
     Carn
    -3.62
    Anth
    -3.38
     anth
    -3.25
     Hend
    -3.24
     Sad
    -3.22
    Amb
    -3.19
     subst
    -3.18
     Nat
    -3.11
     Amb
    -3.10
     Synd
    -3.08
    POSITIVE LOGITS
     6
    4.78
    6
    4.76
    six
    4.20
     Sixth
    4.19
     Six
    4.00
    June
    3.94
    Six
    3.82
     06
    3.82
    06
    3.81
    006
    3.73
    Activations Density 0.111%

    No Known Activations