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. 5-ATT-KK
    6. 35702
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or need

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.13
    1:0.10
    2:0.03
    3:0.04
    4:0.04
    5:0.17
    6:0.03
    7:0.03
    8:0.18
    9:0.06
    10:0.06
    11:0.08
    Negative Logits
    aii
    -1.57
    phia
    -1.50
    externalActionCode
    -1.45
     Survivors
    -1.39
    ensen
    -1.36
    ento
    -1.35
     Cause
    -1.31
     Rodham
    -1.31
    �
    -1.31
     Johnston
    -1.31
    POSITIVE LOGITS
     plenty
    1.65
     quotas
    1.59
     vouchers
    1.49
     theirs
    1.41
     billionaires
    1.38
     options
    1.36
     plentiful
    1.33
     pricey
    1.32
     strict
    1.32
     expensive
    1.31
    Activations Density 0.011%

    No Known Activations