© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 12048
    Prev
    Next
    INDEX
    Explanations

    mathematical and set theory terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mathematical expressions and concepts related to set theory and cardinality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.24
    2:0.08
    3:0.07
    4:0.04
    5:0.06
    6:0.09
    7:0.08
    8:0.05
    9:0.09
    10:0.05
    11:0.05
    Negative Logits
    utenberg
    -2.31
    quished
    -2.00
    owship
    -1.88
    EVA
    -1.77
    ESCO
    -1.76
    mbuds
    -1.72
    arcity
    -1.69
    orio
    -1.65
    awan
    -1.63
     Cosponsors
    -1.62
    POSITIVE LOGITS
    }
    2.14
    }"
    2.07
    »
    2.02
    」
    1.93
    }\
    1.88
    }.
    1.82
    \)
    1.74
    *
    1.67
    },
    1.65
    *,
    1.64
    Activations Density 0.022%

    No Known Activations