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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22301
    Prev
    Next
    INDEX
    Explanations

    topics related to sexual crimes and associated legal discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.08
    2:0.05
    3:0.05
    4:0.04
    5:0.04
    6:0.05
    7:0.16
    8:0.05
    9:0.10
    10:0.18
    11:0.09
    Negative Logits
    Battery
    -1.24
    staking
    -1.19
    lease
    -1.12
    Console
    -1.12
    atform
    -1.09
    ngth
    -1.08
    byss
    -1.08
    volt
    -1.08
    nergy
    -1.05
    版
    -1.00
    POSITIVE LOGITS
     homosexuality
    1.33
     rapists
    1.25
     lesbians
    1.24
     lesbian
    1.24
     adolesc
    1.24
     femin
    1.21
     adolescence
    1.20
    sexual
    1.16
     Boko
    1.16
    utterstock
    1.16
    Activations Density 0.142%

    No Known Activations