© 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. 5-ATT-KK
    6. 35164
    Prev
    Next
    INDEX
    Explanations

    mentions of "and" along with references to girls and female representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.02
    1:0.01
    2:0.07
    3:0.05
    4:0.09
    5:0.03
    6:0.38
    7:0.04
    8:0.03
    9:0.03
    10:0.10
    11:0.08
    Negative Logits
     antioxid
    -1.54
     unfocusedRange
    -1.45
     externalToEVAOnly
    -1.34
    berus
    -1.30
     Wast
    -1.28
    ��
    -1.27
    ETF
    -1.25
     MPG
    -1.23
     pestic
    -1.23
    BRE
    -1.22
    POSITIVE LOGITS
    udi
    1.47
    jong
    1.43
    amate
    1.38
    nikov
    1.34
    otted
    1.29
    bang
    1.28
    anova
    1.27
    boarding
    1.25
    chin
    1.25
    young
    1.25
    Activations Density 0.028%

    No Known Activations