Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8972
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to technological vulnerabilities and security issues

    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
    0:0.03
    1:0.09
    2:0.19
    3:0.03
    4:0.02
    5:0.03
    6:0.06
    7:0.10
    8:0.03
    9:0.03
    10:0.26
    11:0.08
    Negative Logits
    edia
    -2.67
     CODE
    -2.63
    デ
    -2.54
    cens
    -2.53
    cade
    -2.40
    drawn
    -2.39
    Catalog
    -2.34
    258
    -2.24
     censored
    -2.24
    RC
    -2.21
    POSITIVE LOGITS
     Mid
    4.08
    Mid
    3.82
    mid
    3.77
     MID
    3.66
     Middle
    3.36
     mid
    3.21
     Midwest
    3.13
     midrange
    2.98
    Middle
    2.96
     mids
    2.72
    Activations Density 0.001%

    No Known Activations