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. 9030
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
    0:0.13
    1:0.04
    2:0.02
    3:0.08
    4:0.04
    5:0.06
    6:0.06
    7:0.01
    8:0.44
    9:0.05
    10:0.01
    11:0.02
    Negative Logits
    illard
    -1.88
     aggregate
    -1.73
    Motion
    -1.63
     hindsight
    -1.60
    itures
    -1.59
     PRODUCT
    -1.59
     Trib
    -1.58
     combined
    -1.56
     redist
    -1.50
     cents
    -1.49
    POSITIVE LOGITS
    oused
    1.82
     Locked
    1.76
    sleep
    1.72
    76561
    1.61
    lighting
    1.61
    wash
    1.55
    anging
    1.55
     nap
    1.53
     Siren
    1.51
     hostage
    1.50
    Activations Density 0.000%

    No Known Activations