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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22112
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant quantities or measurements

    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
    0:0.07
    1:0.02
    2:0.11
    3:0.13
    4:0.04
    5:0.16
    6:0.06
    7:0.02
    8:0.09
    9:0.09
    10:0.10
    11:0.03
    Negative Logits
    opian
    -1.54
    urnal
    -1.17
    eno
    -1.17
    enary
    -1.14
    oby
    -1.13
    bench
    -1.10
    apor
    -1.09
    inas
    -1.09
    ven
    -1.09
    ypes
    -1.08
    POSITIVE LOGITS
     moreover
    1.10
     comprises
    1.06
     LH
    1.05
     McCartney
    1.04
     Woodward
    1.03
     Md
    1.01
     extraord
    1.00
     IOC
    1.00
     MGM
    0.99
     encompasses
    0.99
    Activations Density 0.303%

    No Known Activations