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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 44428
    Prev
    Next
    INDEX
    Explanations

    references to specific brands or products related to technology and gaming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.08
    1:0.03
    2:0.10
    3:0.12
    4:0.11
    5:0.06
    6:0.10
    7:0.02
    8:0.07
    9:0.12
    10:0.07
    11:0.07
    Negative Logits
    )",
    -1.40
    ',"
    -1.37
    umbn
    -1.34
    "}],"
    -1.34
    catentry
    -1.25
    ),"
    -1.25
    "]
    -1.22
    ],"
    -1.21
    shapeshifter
    -1.20
    ,'"
    -1.19
    POSITIVE LOGITS
    lite
    1.17
     cheap
    1.14
     LIKE
    1.11
     racists
    1.10
     WRITE
    1.10
     Profit
    1.09
     floods
    1.09
     FUCK
    1.07
    eming
    1.06
     RIGHT
    1.05
    Activations Density 0.196%

    No Known Activations