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. 10674
    Prev
    Next
    INDEX
    Explanations

    instances related to illegal activities or environmental concerns

    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
    0:0.11
    1:0.02
    2:0.12
    3:0.25
    4:0.04
    5:0.12
    6:0.02
    7:0.10
    8:0.05
    9:0.02
    10:0.08
    11:0.02
    Negative Logits
     Patron
    -2.31
     Promotion
    -2.08
     congr
    -2.05
     Celebrity
    -1.99
     Partner
    -1.94
    Rating
    -1.92
     winner
    -1.90
     Charisma
    -1.89
     Cancel
    -1.89
     Sponsor
    -1.84
    POSITIVE LOGITS
     gravel
    3.54
     trenches
    3.48
     tunnels
    3.42
     rubble
    3.33
     trees
    3.14
     roofs
    3.12
     holes
    3.09
     bushes
    3.08
     bould
    3.07
     drainage
    3.04
    Activations Density 0.829%

    No Known Activations