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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 35358
    Prev
    Next
    INDEX
    Explanations

    questions or statements addressing the consequences of actions related to wrongdoings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.03
    1:0.02
    2:0.14
    3:0.27
    4:0.09
    5:0.03
    6:0.04
    7:0.07
    8:0.04
    9:0.05
    10:0.08
    11:0.08
    Negative Logits
    ��極
    -1.71
    APTER
    -1.61
    senal
    -1.60
    ".[
    -1.56
    ."[
    -1.54
    externalActionCode
    -1.50
    }}}
    -1.46
     Ukrain
    -1.45
     Pwr
    -1.45
    ��
    -1.39
    POSITIVE LOGITS
    ?)
    2.20
    ?
    2.08
    ?:
    2.06
    ?'
    1.97
    ?
    1.87
    ?),
    1.80
    ?).
    1.78
    )?
    1.75
    ??
    1.75
    ?'"
    1.75
    Activations Density 0.073%

    No Known Activations