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. 22304
    Prev
    Next
    INDEX
    Explanations

    phrases related to political actions or positions

    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
    0:0.04
    1:0.04
    2:0.12
    3:0.08
    4:0.03
    5:0.15
    6:0.20
    7:0.04
    8:0.07
    9:0.09
    10:0.06
    11:0.03
    Negative Logits
     Pix
    -1.35
     })
    -1.32
     ($)
    -1.26
     -->
    -1.26
    ...)
    -1.23
     });
    -1.19
     Osiris
    -1.15
     Brawl
    -1.15
     CLR
    -1.15
     Examiner
    -1.14
    POSITIVE LOGITS
    "))
    1.78
    ONSORED
    1.55
    ajo
    1.40
    usalem
    1.40
    jew
    1.39
    milo
    1.39
    vae
    1.39
    igious
    1.34
    uez
    1.30
    daq
    1.30
    Activations Density 0.002%

    No Known Activations