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. 189
    Prev
    Next
    INDEX
    Explanations

    phrases indicating expectations or predictions, particularly in a political context

    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
    0:0.04
    1:0.02
    2:0.08
    3:0.04
    4:0.09
    5:0.04
    6:0.18
    7:0.09
    8:0.06
    9:0.22
    10:0.02
    11:0.07
    Negative Logits
    plet
    -3.93
     Dirk
    -3.64
    arden
    -3.54
    oultry
    -3.27
    bird
    -3.26
     bird
    -3.24
     Arkansas
    -3.21
    birds
    -3.16
     poultry
    -3.13
     Gast
    -3.12
    POSITIVE LOGITS
     Modi
    9.47
    Mod
    6.15
     Gujarat
    5.49
     Narendra
    5.40
     BJP
    4.96
     Mod
    4.36
     Gujar
    4.21
     Patel
    4.15
    MOD
    4.09
     Sharif
    4.08
    Activations Density 0.014%

    No Known Activations