Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 9109
    Prev
    Next
    INDEX
    Explanations

    phrases related to political actions and implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.05
    2:0.02
    3:0.12
    4:0.07
    5:0.06
    6:0.08
    7:0.03
    8:0.08
    9:0.36
    10:0.02
    11:0.01
    Negative Logits
    Information
    -1.71
    lict
    -1.71
    Contents
    -1.69
    Initial
    -1.66
    visory
    -1.64
    aea
    -1.63
    quartered
    -1.62
    ć
    -1.62
    ahime
    -1.60
     Closed
    -1.58
    POSITIVE LOGITS
     damn
    2.16
     darn
    2.11
     damned
    2.07
     goddamn
    2.02
     thereafter
    1.82
     fools
    1.69
     hasht
    1.69
     Suicide
    1.66
     caval
    1.63
     downright
    1.61
    Activations Density 0.557%

    No Known Activations