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. 9-ATT-KK
    6. 41
    Prev
    Next
    INDEX
    Explanations

    instances of significant legal actions or consequences

    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
    0:0.05
    1:0.03
    2:0.06
    3:0.13
    4:0.05
    5:0.12
    6:0.05
    7:0.07
    8:0.06
    9:0.03
    10:0.06
    11:0.24
    Negative Logits
     Riy
    -3.01
     honoured
    -2.97
     Isis
    -2.86
     apologised
    -2.83
     recognise
    -2.83
     semblance
    -2.82
     maths
    -2.78
     organising
    -2.75
     recognised
    -2.66
     favourite
    -2.63
    POSITIVE LOGITS
    ●
    4.91
    �
    4.87
    »
    4.83
    </
    4.76
    」
    4.75
    �
    4.64
    ***
    4.58
    ►
    4.53
    �
    4.50
    ­
    4.48
    Activations Density 0.290%

    No Known Activations