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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11199
    Prev
    Next
    INDEX
    Explanations

    information related to financial transactions and contributions

    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
    0:0.03
    1:0.09
    2:0.03
    3:0.08
    4:0.07
    5:0.04
    6:0.03
    7:0.08
    8:0.05
    9:0.03
    10:0.07
    11:0.33
    Negative Logits
    —"
    -3.37
    �
    -3.31
     ­
    -3.26
    »
    -3.15
    .—
    -3.09
    >]
    -3.00
    "—
    -2.91
    *:
    -2.87
    )—
    -2.84
    —
    -2.79
    POSITIVE LOGITS
     doesnt
    3.63
     alot
    3.60
     dont
    3.29
     thats
    3.19
     whilst
    3.07
     didnt
    3.03
     whats
    3.02
     wont
    2.90
     etc
    2.71
     haha
    2.63
    Activations Density 0.889%

    No Known Activations