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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 8885
    Prev
    Next
    INDEX
    Explanations

    the action of orientation or direction, particularly in a global or contextual sense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.08
    2:0.07
    3:0.09
    4:0.08
    5:0.07
    6:0.07
    7:0.08
    8:0.08
    9:0.09
    10:0.07
    11:0.08
    Negative Logits
    ズ
    -2.33
    itech
    -2.24
    mble
    -2.21
    sil
    -2.19
    capacity
    -2.15
     Orche
    -2.08
    pkg
    -2.07
    ulet
    -2.05
    ulator
    -2.04
    ectomy
    -2.04
    POSITIVE LOGITS
     ted
    2.83
    SPONSORED
    2.39
    ometimes
    2.35
     Ichigo
    2.34
     describ
    2.29
     harsher
    2.17
     MUCH
    2.15
     wonder
    2.15
     doubt
    2.15
     detrim
    2.14
    Activations Density 0.000%

    No Known Activations