© 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. 19062
    Prev
    Next
    INDEX
    Explanations

    instances of discussions around consent and its implications in both legal and personal contexts

    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
    0:0.10
    1:0.03
    2:0.27
    3:0.09
    4:0.04
    5:0.12
    6:0.07
    7:0.05
    8:0.03
    9:0.09
    10:0.05
    11:0.01
    Negative Logits
     millionaires
    -2.65
    tal
    -2.55
    aunts
    -2.44
     Hebdo
    -2.40
    jiang
    -2.38
    secut
    -2.33
     Pik
    -2.30
    ihu
    -2.30
     Beard
    -2.29
     Typhoon
    -2.27
    POSITIVE LOGITS
     consent
    6.76
     Consent
    6.74
     consensual
    4.71
     condom
    4.06
     authorization
    3.56
     permission
    3.44
     voluntary
    3.37
     orgasm
    3.30
     coercion
    3.29
     coercive
    3.22
    Activations Density 0.048%

    No Known Activations