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. 7-ATT-KK
    6. 9096
    Prev
    Next
    INDEX
    Explanations

    phrases that reflect the quality and effectiveness of someone's work or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.16
    1:0.07
    2:0.00
    3:0.19
    4:0.10
    5:0.18
    6:0.03
    7:0.01
    8:0.08
    9:0.09
    10:0.02
    11:0.02
    Negative Logits
     prohibited
    -1.64
    etermined
    -1.58
     Piercing
    -1.58
     forbidden
    -1.56
     indefinite
    -1.56
     contestant
    -1.52
    heid
    -1.52
     Clim
    -1.52
     revoked
    -1.49
     indefinitely
    -1.49
    POSITIVE LOGITS
    erning
    2.15
    pb
    1.95
    amera
    1.94
    mop
    1.90
    uristic
    1.86
    nyder
    1.72
    lda
    1.72
    abase
    1.71
     empath
    1.71
    average
    1.67
    Activations Density 0.025%

    No Known Activations