© 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. 480
    Prev
    Next
    INDEX
    Explanations

    terms related to consequences and implications of actions or events

    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
    0:0.30
    1:0.01
    2:0.19
    3:0.06
    4:0.03
    5:0.04
    6:0.02
    7:0.03
    8:0.02
    9:0.02
    10:0.20
    11:0.02
    Negative Logits
     malfunction
    -2.30
     flawless
    -2.27
     remod
    -2.26
     refurb
    -2.25
     reclaim
    -2.23
     incompet
    -2.23
     reclaimed
    -2.22
     complying
    -2.22
     warranty
    -2.17
     struggling
    -2.17
    POSITIVE LOGITS
     ramifications
    2.90
     implications
    2.64
    Draft
    2.25
     consequences
    2.21
    lethal
    2.20
    hammer
    2.19
     GOODMAN
    2.18
    entially
    2.14
    Hor
    2.14
     Yiannopoulos
    2.12
    Activations Density 0.015%

    No Known Activations