© 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. 5-ATT-KK
    6. 35667
    Prev
    Next
    INDEX
    Explanations

    acronyms or abbreviations related to organizations or events

    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
    0:0.04
    1:0.34
    2:0.03
    3:0.04
    4:0.03
    5:0.24
    6:0.05
    7:0.02
    8:0.03
    9:0.05
    10:0.05
    11:0.03
    Negative Logits
     sc
    -1.87
     Sect
    -1.82
     tang
    -1.80
     mars
    -1.73
     Invaders
    -1.71
     sv
    -1.68
     celebr
    -1.67
     helic
    -1.63
     cx
    -1.63
     solicit
    -1.62
    POSITIVE LOGITS
    one
    2.44
    ano
    2.40
    onne
    2.30
    onian
    2.20
    ANY
    2.19
    iour
    2.15
    ania
    2.14
    ONE
    2.12
    ON
    2.08
    oning
    2.04
    Activations Density 0.001%

    No Known Activations