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. 11202
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize exclusivity or limitation

    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
    0:0.08
    1:0.06
    2:0.09
    3:0.08
    4:0.07
    5:0.07
    6:0.09
    7:0.09
    8:0.09
    9:0.07
    10:0.08
    11:0.07
    Negative Logits
     Spike
    -2.86
     Slayer
    -2.81
     Dagger
    -2.78
     Blink
    -2.76
     Clip
    -2.76
     Laurel
    -2.54
     Oaks
    -2.52
     Vic
    -2.50
     Whedon
    -2.49
     Skull
    -2.49
    POSITIVE LOGITS
    renheit
    3.48
    ouver
    3.03
    ieth
    2.89
    rade
    2.71
    eur
    2.60
    ondon
    2.60
    orld
    2.58
    weather
    2.58
    oward
    2.58
    vous
    2.57
    Activations Density 0.000%

    No Known Activations