© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 4079
    Prev
    Next
    INDEX
    Explanations

    references to societal critiques or discussions surrounding inequality and power dynamics

    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
    0:0.05
    1:0.05
    2:0.04
    3:0.05
    4:0.05
    5:0.07
    6:0.05
    7:0.04
    8:0.09
    9:0.04
    10:0.04
    11:0.38
    Negative Logits
     defences
    -3.02
     realise
    -2.88
     Isis
    -2.78
     realised
    -2.69
     honoured
    -2.63
     Nasa
    -2.62
     armoured
    -2.61
     favourable
    -2.56
     Ottawa
    -2.53
     favourite
    -2.52
    POSITIVE LOGITS
    ––
    6.79
    ----
    5.28
    --------------------
    5.11
    --------
    5.10
            
    4.91
        
    4.77
     -------
    4.65
    -------------
    4.64
                    
    4.63
     --------
    4.58
    Activations Density 0.000%

    No Known Activations