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. 173
    Prev
    Next
    INDEX
    Explanations

    phrases related to support for podcasts and music bands

    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
    0:0.42
    1:0.01
    2:0.05
    3:0.07
    4:0.06
    5:0.08
    6:0.04
    7:0.07
    8:0.05
    9:0.04
    10:0.04
    11:0.02
    Negative Logits
     shading
    -2.77
     Lauder
    -2.69
     bathing
    -2.52
     Bane
    -2.47
    picture
    -2.47
     glare
    -2.42
    urga
    -2.40
    soType
    -2.39
     Granger
    -2.38
     blinded
    -2.35
    POSITIVE LOGITS
    podcast
    6.54
     podcasts
    6.29
     podcast
    6.16
     Podcast
    6.15
    odcast
    5.76
     listeners
    5.54
     listener
    5.19
     pod
    5.09
    pod
    4.93
     iTunes
    4.72
    Activations Density 0.125%

    No Known Activations