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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 44095
    Prev
    Next
    INDEX
    Explanations

    phrases introducing characteristics or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.07
    2:0.07
    3:0.07
    4:0.08
    5:0.08
    6:0.09
    7:0.09
    8:0.08
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
    uyomi
    -2.23
    ��
    -2.18
    keyes
    -1.92
    glers
    -1.89
    jri
    -1.89
    ursions
    -1.84
    ashtra
    -1.83
    vable
    -1.81
    ��
    -1.80
     sqor
    -1.80
    POSITIVE LOGITS
    Diamond
    1.93
    Cond
    1.76
     sexist
    1.75
     homophobic
    1.74
    Interstitial
    1.70
     QC
    1.69
     stating
    1.65
    Recommend
    1.65
     wherein
    1.64
     casting
    1.61
    Activations Density 0.000%

    No Known Activations