© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22740
    Prev
    Next
    INDEX
    Explanations

    topics related to documented events or incidents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of visual representation or display of events and data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.03
    2:0.06
    3:0.06
    4:0.04
    5:0.07
    6:0.05
    7:0.09
    8:0.18
    9:0.06
    10:0.15
    11:0.07
    Negative Logits
    ��
    -1.25
    ��
    -1.17
     sugg
    -0.96
     myster
    -0.95
    ��
    -0.95
     acknowled
    -0.94
    levard
    -0.94
     Carbuncle
    -0.93
    ��
    -0.92
     Recomm
    -0.90
    POSITIVE LOGITS
     resemblance
    0.96
    abs
    0.94
     dstg
    0.93
    aily
    0.93
     similarities
    0.91
    bleacher
    0.90
    lip
    0.86
    rough
    0.85
    awed
    0.84
    below
    0.83
    Activations Density 0.149%

    No Known Activations