© 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. 22796
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms and descriptions, particularly related to research studies and medical conditions

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

    references to specific personality traits or characteristics

    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
    2:0.31
    3:0.06
    4:0.16
    5:0.05
    6:0.02
    7:0.03
    8:0.05
    9:0.12
    10:0.05
    11:0.02
    Negative Logits
    ADRA
    -1.39
     Frie
    -1.33
    ovember
    -1.30
    abee
    -1.23
     ILCS
    -1.22
    odore
    -1.22
     juven
    -1.21
    ahon
    -1.20
    orno
    -1.20
    catentry
    -1.20
    POSITIVE LOGITS
    hare
    1.38
    lishes
    1.37
     Lights
    1.34
    tails
    1.31
    adders
    1.26
    tailed
    1.23
    twitch
    1.22
    strap
    1.18
    sent
    1.18
    hedral
    1.17
    Activations Density 0.004%

    No Known Activations