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. 9124
    Prev
    Next
    INDEX
    Explanations

    references to social media, legal actions, and various forms of creative content

    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
    0:0.40
    1:0.04
    2:0.01
    3:0.08
    4:0.08
    5:0.11
    6:0.03
    7:0.01
    8:0.10
    9:0.07
    10:0.01
    11:0.01
    Negative Logits
    acea
    -1.88
    abase
    -1.76
    pter
    -1.66
    ellect
    -1.63
    uana
    -1.63
    ptin
    -1.61
    etus
    -1.60
    aminer
    -1.60
     parity
    -1.58
    maxwell
    -1.58
    POSITIVE LOGITS
    izations
    2.38
     observations
    2.18
     snapshots
    2.12
     engagements
    2.11
     discoveries
    2.07
     interventions
    2.06
    isations
    2.03
     assessments
    2.02
    ements
    1.98
     announcements
    1.98
    Activations Density 0.066%

    No Known Activations