© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10555
    Prev
    Next
    INDEX
    Explanations

    the word "down."

    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
    0:0.06
    1:0.09
    2:0.09
    3:0.08
    4:0.07
    5:0.07
    6:0.09
    7:0.09
    8:0.07
    9:0.09
    10:0.07
    11:0.07
    Negative Logits
     polish
    -2.68
    ionage
    -2.59
    estern
    -2.50
    ÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂ
    -2.43
     +#
    -2.32
     Meier
    -2.31
    cks
    -2.30
     colored
    -2.27
     underwater
    -2.27
     decorated
    -2.23
    POSITIVE LOGITS
     Baxter
    2.74
    Leary
    2.59
    iasis
    2.50
    BuyableInstoreAndOnline
    2.48
     CBD
    2.47
     Katherine
    2.44
     Becky
    2.41
    版
    2.41
     Jane
    2.39
     Bris
    2.39
    Activations Density 0.000%

    No Known Activations