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. 9-ATT-KK
    6. 341
    Prev
    Next
    INDEX
    Explanations

    key names and terms associated with fantasy literature and cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.03
    2:0.07
    3:0.30
    4:0.03
    5:0.06
    6:0.03
    7:0.04
    8:0.04
    9:0.03
    10:0.23
    11:0.03
    Negative Logits
     sequences
    -2.39
     shapes
    -2.28
     strains
    -2.27
     stages
    -2.20
     groups
    -2.17
    roups
    -2.15
     scenarios
    -2.11
     phrases
    -2.10
     configurations
    -2.10
     flavors
    -2.09
    POSITIVE LOGITS
    uracy
    2.36
    '?
    2.30
    aldo
    2.22
    )).
    2.16
    ?'
    2.07
    )?
    2.05
     valuation
    2.04
    visor
    2.04
    efficiency
    2.04
     vitality
    2.03
    Activations Density 0.006%

    No Known Activations