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. 7-ATT-KK
    6. 9236
    Prev
    Next
    INDEX
    Explanations

    instances of expressions related to discomfort or disagreement with social 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
    0:0.05
    1:0.04
    2:0.02
    3:0.03
    4:0.03
    5:0.06
    6:0.17
    7:0.02
    8:0.03
    9:0.03
    10:0.01
    11:0.47
    Negative Logits
    senal
    -3.40
     APPLIC
    -2.79
    DragonMagazine
    -2.58
    ccording
    -2.35
    76561
    -2.27
    ロ
    -2.26
    topic
    -2.23
    ティ
    -2.22
    Subject
    -2.21
    ザ
    -2.17
    POSITIVE LOGITS
     sweat
    2.20
     guts
    2.12
     chops
    1.98
     ripple
    1.92
     screams
    1.90
     slam
    1.86
    zin
    1.85
     shrink
    1.84
     Rae
    1.81
     weigh
    1.81
    Activations Density 0.047%

    No Known Activations