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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20659
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversy and disagreement

    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
    2:0.04
    3:0.09
    4:0.07
    5:0.06
    6:0.04
    7:0.06
    8:0.15
    9:0.02
    10:0.04
    11:0.32
    Negative Logits
      
    -3.71
        
    -3.56
     (£
    -3.53
    ".[
    -3.25
     
    -3.24
            
    -3.22
                    
    -3.14
     £
    -3.08
     [...]
    -2.93
       
    -2.87
    POSITIVE LOGITS
    ↵
    3.29
    afort
    2.41
    <|endoftext|>
    2.40
    imens
    2.38
    Senate
    2.36
    ILA
    2.34
    !"
    2.32
    izabeth
    2.31
    thia
    2.31
    opal
    2.30
    Activations Density 0.005%

    No Known Activations