© 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. 22712
    Prev
    Next
    INDEX
    Explanations

    information about scientific research projects and goals

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

    goal-oriented phrases indicating intentions or actions

    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
    0:0.07
    1:0.03
    2:0.09
    3:0.05
    4:0.28
    5:0.07
    6:0.04
    7:0.02
    8:0.07
    9:0.13
    10:0.07
    11:0.03
    Negative Logits
    chev
    -1.55
    orthodox
    -1.51
    RAW
    -1.48
    robat
    -1.40
    fe
    -1.39
    emp
    -1.37
    Guard
    -1.31
    rounder
    -1.30
    rou
    -1.30
    pert
    -1.29
    POSITIVE LOGITS
     limiting
    1.66
    uate
    1.58
     qualitative
    1.47
    ��
    1.46
    ォ
    1.43
     {:
    1.37
     Reward
    1.35
     abstinence
    1.33
     mathemat
    1.31
     optimization
    1.29
    Activations Density 0.020%

    No Known Activations