© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 4031
    Prev
    Next
    INDEX
    Explanations

    expressions related to the concept of voice and being heard

    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
    0:0.44
    1:0.02
    2:0.14
    3:0.09
    4:0.02
    5:0.05
    6:0.03
    7:0.04
    8:0.03
    9:0.03
    10:0.06
    11:0.01
    Negative Logits
     photos
    -2.40
     img
    -2.38
     Photoshop
    -2.38
    images
    -2.33
    isoft
    -2.32
     pics
    -2.28
     Solitaire
    -2.26
    Credit
    -2.23
     redesign
    -2.22
     designs
    -2.17
    POSITIVE LOGITS
    voice
    5.52
     voice
    5.29
     voices
    5.02
    Voice
    4.99
     Voices
    4.88
     listeners
    4.79
     speakers
    4.75
     louder
    4.73
     voic
    4.70
     Voice
    4.69
    Activations Density 0.174%

    No Known Activations