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. 7608
    Prev
    Next
    INDEX
    Explanations

    terms related to financial misconduct or fraud

    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
    0:0.10
    1:0.02
    2:0.12
    3:0.13
    4:0.07
    5:0.23
    6:0.03
    7:0.12
    8:0.03
    9:0.03
    10:0.04
    11:0.03
    Negative Logits
     behavi
    -1.96
     coward
    -1.93
    abiding
    -1.90
     stupidity
    -1.79
    ottesville
    -1.74
     bullies
    -1.74
     bully
    -1.74
    EStream
    -1.72
    ============
    -1.72
    enment
    -1.71
    POSITIVE LOGITS
     canceled
    1.68
     Hawaiian
    1.63
     Mau
    1.56
     Haitian
    1.55
     cancellation
    1.50
     refunds
    1.50
    raft
    1.48
     awarding
    1.47
     applications
    1.46
     Aval
    1.44
    Activations Density 1.006%

    No Known Activations