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. 157
    Prev
    Next
    INDEX
    Explanations

    aspects related to confirmations or assertions within a context

    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
    0:0.04
    1:0.07
    2:0.04
    3:0.08
    4:0.06
    5:0.06
    6:0.12
    7:0.05
    8:0.05
    9:0.06
    10:0.06
    11:0.26
    Negative Logits
     #
    -3.84
    #
    -3.48
     +
    -2.96
     ##
    -2.92
     +#
    -2.75
     �
    -2.74
     �
    -2.63
     >
    -2.63
    ​​
    -2.60
    [/
    -2.58
    POSITIVE LOGITS
    .")
    3.69
    .)
    3.32
    ),"
    3.18
    .,"
    3.06
    )."
    3.06
    —"
    2.98
    .).
    2.89
    .),
    2.86
     ));
    2.85
     …"
    2.61
    Activations Density 0.000%

    No Known Activations