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. 2-ATT-KK
    6. 13714
    Prev
    Next
    INDEX
    Explanations

    names of people or groups

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.07
    1:0.02
    2:0.06
    3:0.09
    4:0.02
    5:0.12
    6:0.06
    7:0.09
    8:0.10
    9:0.08
    10:0.16
    11:0.08
    Negative Logits
    benefit
    -1.00
     Aval
    -0.95
    EStream
    -0.86
    グ
    -0.85
     NETWORK
    -0.83
     �
    -0.80
     AND
    -0.78
     behav
    -0.76
    manac
    -0.76
    ogeneity
    -0.75
    POSITIVE LOGITS
     respectively
    1.38
     alike
    1.07
    ospons
    0.99
     finishes
    0.98
     Streets
    0.94
    osponsors
    0.93
     Lines
    0.88
    esson
    0.85
    )|
    0.80
    undai
    0.80
    Activations Density 0.502%

    No Known Activations