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. 18618
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific character sequences or names

    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
    1:0.05
    2:0.05
    3:0.07
    4:0.06
    5:0.06
    6:0.16
    7:0.05
    8:0.06
    9:0.24
    10:0.04
    11:0.06
    Negative Logits
    lt
    -3.39
    lr
    -3.38
    rolet
    -3.29
    isal
    -3.10
     Lyft
    -3.03
    llah
    -2.94
    ract
    -2.93
    ohl
    -2.82
     Claudia
    -2.78
    ilet
    -2.77
    POSITIVE LOGITS
     missionaries
    2.95
     Portug
    2.93
     newsp
    2.76
     jour
    2.75
     Towns
    2.64
     migrated
    2.62
     Empires
    2.59
     Spartans
    2.54
     pudding
    2.49
    Poly
    2.47
    Activations Density 0.000%

    No Known Activations