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. 9578
    Prev
    Next
    INDEX
    Explanations

    reports and statements concerning findings, conclusions, and evaluations

    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
    0:0.06
    1:0.09
    2:0.03
    3:0.21
    4:0.15
    5:0.07
    6:0.05
    7:0.01
    8:0.07
    9:0.14
    10:0.03
    11:0.03
    Negative Logits
    �
    -1.58
     anymore
    -1.57
     bount
    -1.53
    Buff
    -1.53
     quota
    -1.48
     proble
    -1.45
    jobs
    -1.42
    NPR
    -1.42
     jobs
    -1.42
     Buffer
    -1.40
    POSITIVE LOGITS
     concludes
    2.09
    ="#
    1.90
    intendent
    1.79
     implying
    1.64
    }.
    1.63
     conclude
    1.60
    orius
    1.59
     imply
    1.54
     alluded
    1.52
    emphasis
    1.52
    Activations Density 0.044%

    No Known Activations