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. 9-ATT-KK
    6. 7680
    Prev
    Next
    INDEX
    Explanations

    phrases indicating past experiences or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.01
    2:0.07
    3:0.13
    4:0.02
    5:0.05
    6:0.09
    7:0.04
    8:0.02
    9:0.03
    10:0.35
    11:0.05
    Negative Logits
     inferior
    -2.41
     unfit
    -2.34
     deteriorating
    -2.17
     precarious
    -2.16
     destiny
    -2.14
     doomed
    -2.12
     disadvantage
    -2.12
     dignity
    -2.11
     accordingly
    -2.10
     unworthy
    -2.09
    POSITIVE LOGITS
    >)
    2.91
     experimented
    2.85
     heard
    2.63
    76561
    2.61
     VIDEOS
    2.52
     mentioned
    2.46
     noticed
    2.44
     mentions
    2.43
    ��
    2.42
    ��
    2.40
    Activations Density 0.053%

    No Known Activations