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

    Neuronpedia

    Jacobian LensNEW
    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. 13607
    Prev
    Next
    INDEX
    Explanations

    phrases indicating divisions or contrasts within a community or society

    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
    0:0.08
    1:0.01
    2:0.05
    3:0.24
    4:0.02
    5:0.04
    6:0.02
    7:0.03
    8:0.04
    9:0.01
    10:0.38
    11:0.02
    Negative Logits
     offline
    -2.42
     unus
    -2.35
     humiliated
    -2.30
    DERR
    -2.12
    disabled
    -2.07
     revoked
    -2.03
     harmed
    -2.01
     ruined
    -1.99
     insulted
    -1.98
     canceled
    -1.96
    POSITIVE LOGITS
     continuum
    2.54
     lines
    2.51
    paralle
    2.41
     vein
    2.40
     directions
    2.19
     lineage
    2.16
     parallels
    2.12
    �
    2.11
    ourke
    2.09
     direction
    2.09
    Activations Density 0.008%

    No Known Activations