© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 387
    Prev
    Next
    INDEX
    Explanations

    themes related to decision-making and success in professional contexts

    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
    1:0.05
    2:0.06
    3:0.14
    4:0.03
    5:0.07
    6:0.02
    7:0.05
    8:0.02
    9:0.03
    10:0.39
    11:0.03
    Negative Logits
    undreds
    -2.41
    ‎
    -2.27
    unknown
    -2.25
    fourth
    -2.14
    fifth
    -2.11
     indefinitely
    -2.10
    without
    -2.09
    outside
    -2.00
    ometer
    -1.98
    esides
    -1.95
    POSITIVE LOGITS
     corresponds
    2.25
     speedy
    2.24
    ASY
    2.19
     responds
    2.17
     agrees
    2.15
     suitable
    2.11
    iquette
    2.04
     acceptable
    2.01
     advisable
    2.00
     obey
    1.97
    Activations Density 0.035%

    No Known Activations