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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20683
    Prev
    Next
    INDEX
    Explanations

    direct speech or quotations from characters in a narrative context

    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
    0:0.03
    1:0.05
    2:0.05
    3:0.06
    4:0.04
    5:0.07
    6:0.03
    7:0.07
    8:0.07
    9:0.03
    10:0.06
    11:0.37
    Negative Logits
    ?]
    -3.98
    !]
    -3.81
    ,)
    -3.76
    "]
    -3.69
    }}
    -3.63
    Enlarge
    -3.54
     )]
    -3.52
    .]
    -3.40
     }}
    -3.31
    .}
    -3.28
    POSITIVE LOGITS
    :-
    3.75
    :
    3.65
     Nasa
    3.51
    *:
    3.44
     Nato
    3.41
     programme
    3.00
     programmes
    2.92
    ':
    2.88
     organisers
    2.83
     enqu
    2.80
    Activations Density 0.007%

    No Known Activations