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. 7-ATT-KK
    6. 8978
    Prev
    Next
    INDEX
    Explanations

    references to musical bands or artists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.08
    2:0.07
    3:0.08
    4:0.08
    5:0.06
    6:0.08
    7:0.10
    8:0.06
    9:0.08
    10:0.10
    11:0.07
    Negative Logits
    uca
    -2.34
    baum
    -2.15
    Miller
    -2.11
    agos
    -2.08
    sch
    -2.07
    bold
    -2.06
    tex
    -2.05
    anca
    -2.03
    trace
    -2.02
    Jackson
    -2.00
    POSITIVE LOGITS
     airstrikes
    2.44
     Vaj
    2.26
     overfl
    2.15
     Rohing
    1.98
     "$:/
    1.97
     workouts
    1.96
     rollout
    1.96
     polls
    1.92
     cooldown
    1.88
     combos
    1.86
    Activations Density 0.000%

    No Known Activations