Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 7534
    Prev
    Next
    INDEX
    Explanations

    references to age and legal definitions surrounding sexual consent

    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
    0:0.03
    1:0.02
    2:0.20
    3:0.06
    4:0.06
    5:0.10
    6:0.12
    7:0.06
    8:0.12
    9:0.04
    10:0.08
    11:0.05
    Negative Logits
    生
    -1.83
     ⓘ
    -1.58
    ipel
    -1.56
    ��
    -1.49
     Cabin
    -1.46
    �
    -1.46
     Shutterstock
    -1.43
    assetsadobe
    -1.42
     Inher
    -1.40
    BG
    -1.35
    POSITIVE LOGITS
     ILCS
    1.67
    iple
    1.63
    pound
    1.57
    depending
    1.55
    daq
    1.53
    fold
    1.52
    endment
    1.51
    clad
    1.50
    utive
    1.49
    mile
    1.49
    Activations Density 0.000%

    No Known Activations