© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10755
    Prev
    Next
    INDEX
    Explanations

    references to news articles and associated media elements like photos and images

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.18
    2:0.01
    3:0.03
    4:0.11
    5:0.08
    6:0.05
    7:0.16
    8:0.04
    9:0.02
    10:0.16
    11:0.04
    Negative Logits
    )))
    -2.56
    76561
    -2.40
    )).
    -2.40
     �
    -2.33
     thereafter
    -2.31
    bows
    -2.31
    alities
    -2.30
    )),
    -2.22
    ]).
    -2.20
     respectively
    -2.18
    POSITIVE LOGITS
    asar
    2.35
    assium
    2.15
     Hopkins
    2.11
     Johannes
    2.08
     Image
    2.04
     dstg
    2.04
     Carrier
    1.99
     Klaus
    1.92
    lesh
    1.88
     Crypto
    1.87
    Activations Density 0.008%

    No Known Activations