© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 18454
    Prev
    Next
    INDEX
    Explanations

    phrases and terms that relate to fairness and equality

    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
    1:0.02
    2:0.06
    3:0.16
    4:0.02
    5:0.05
    6:0.03
    7:0.04
    8:0.03
    9:0.02
    10:0.45
    11:0.03
    Negative Logits
     adversely
    -2.70
     detrimental
    -2.53
     detriment
    -2.44
     indirectly
    -2.40
     negatively
    -2.39
     unnecessarily
    -2.38
     heavily
    -2.31
     disproportionately
    -2.31
     decreases
    -2.30
     unlawfully
    -2.29
    POSITIVE LOGITS
    Ready
    2.59
    omen
    2.47
    perfect
    2.43
    ready
    2.32
     Ready
    2.28
    bright
    2.27
    ]}
    2.25
    onomy
    2.22
    ��
    2.21
    worthiness
    2.19
    Activations Density 0.030%

    No Known Activations