© 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. 22662
    Prev
    Next
    INDEX
    Explanations

    guidance or warnings regarding potential risks or consequences

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

    references to risks and tests related to decision-making

    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
    2:0.05
    3:0.06
    4:0.03
    5:0.06
    6:0.02
    7:0.07
    8:0.31
    9:0.07
    10:0.12
    11:0.07
    Negative Logits
    lege
    -1.41
    gement
    -1.27
    venge
    -1.25
     cannabin
    -1.24
    hammad
    -1.24
     nuance
    -1.19
     temperament
    -1.19
    soType
    -1.19
    namese
    -1.16
     furry
    -1.15
    POSITIVE LOGITS
    bench
    1.46
     benchmarks
    1.36
     Swan
    1.33
    },{"
    1.32
     Villa
    1.28
     tests
    1.20
    Bench
    1.18
     Milan
    1.17
     Tests
    1.15
     Marathon
    1.12
    Activations Density 0.067%

    No Known Activations