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. 11404
    Prev
    Next
    INDEX
    Explanations

    references to prison systems and their operations

    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
    1:0.01
    2:0.44
    3:0.07
    4:0.02
    5:0.10
    6:0.04
    7:0.05
    8:0.06
    9:0.02
    10:0.02
    11:0.01
    Negative Logits
     pollen
    -3.13
     Flare
    -2.69
     eclipse
    -2.67
     Meteor
    -2.60
     comet
    -2.49
     sunscreen
    -2.44
     Fnatic
    -2.40
     Doodle
    -2.40
     Valent
    -2.37
     Rumble
    -2.35
    POSITIVE LOGITS
    prison
    6.67
     inmate
    6.66
     jails
    6.56
     prisoners
    6.51
     prison
    6.49
     inmates
    6.46
     incarcer
    6.45
     prisoner
    6.44
     Prison
    6.41
     prisons
    6.36
    Activations Density 0.842%

    No Known Activations