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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22931
    Prev
    Next
    INDEX
    Explanations

    topics related to diverse social and political issues or events

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

    occurrences of the phrase "of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.02
    2:0.11
    3:0.08
    4:0.26
    5:0.09
    6:0.03
    7:0.02
    8:0.10
    9:0.13
    10:0.05
    11:0.02
    Negative Logits
    horn
    -1.34
    umption
    -1.25
    atoon
    -1.25
    rab
    -1.24
     themes
    -1.19
     minded
    -1.17
    sites
    -1.15
    hots
    -1.13
    Aim
    -1.09
    uga
    -1.08
    POSITIVE LOGITS
     subtract
    1.82
     conclud
    1.51
     [];
    1.43
    ERO
    1.35
    ADRA
    1.27
    AMI
    1.21
     accum
    1.20
     Calculator
    1.20
     CPR
    1.20
     Either
    1.19
    Activations Density 0.006%

    No Known Activations