Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22646
    Prev
    Next
    INDEX
    Explanations

    mentions of a niche or a specialized area within a broader field

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

    references to energy-related topics and political discussions surrounding those issues

    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
    0:0.05
    1:0.03
    2:0.14
    3:0.09
    4:0.14
    5:0.09
    6:0.02
    7:0.03
    8:0.07
    9:0.20
    10:0.06
    11:0.03
    Negative Logits
     Nieto
    -1.33
     towed
    -1.30
     Probe
    -1.18
    amaz
    -1.16
    ILA
    -1.14
     toll
    -1.14
     Winchester
    -1.13
     destro
    -1.12
    PDATE
    -1.10
    rael
    -1.10
    POSITIVE LOGITS
    holders
    1.44
    ieties
    1.40
    mens
    1.39
     competitors
    1.33
    interstitial
    1.30
    asty
    1.27
    bies
    1.24
    seekers
    1.23
    genre
    1.22
    roller
    1.20
    Activations Density 0.002%

    No Known Activations