© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22761
    Prev
    Next
    INDEX
    Explanations

    references to news, whistleblowing, and governmental actions

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

    themes related to social progress and community support

    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
    0:0.10
    1:0.04
    2:0.07
    3:0.08
    4:0.04
    5:0.13
    6:0.08
    7:0.04
    8:0.11
    9:0.11
    10:0.11
    11:0.04
    Negative Logits
    argon
    -1.31
    omon
    -1.24
    ODUCT
    -1.20
    モ
    -1.18
    ints
    -1.17
    -+-+
    -1.14
    chan
    -1.14
     transformations
    -1.13
    ████
    -1.10
    division
    -1.09
    POSITIVE LOGITS
     Pru
    1.19
     strapped
    1.17
     Barton
    1.16
    CVE
    1.14
    EStreamFrame
    1.14
     Accessed
    1.14
    "],"
    1.13
    .>>
    1.12
     Cadillac
    1.08
     NTS
    1.07
    Activations Density 0.000%

    No Known Activations