INDEX

Explanations

terms related to travel and trips

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

herited

-0.62

солю

-0.60

 esternos

-0.59

 Princip

-0.57

 Linde

-0.57

landais

-0.56

stander

-0.55

estruct

-0.54

Amm

-0.54

 vĩnh

-0.53

POSITIVE LOGITS

GroupLayout

0.69

Xna

0.68

 travelers

0.67

ogue

0.66

 Travelers

0.66

WriteBarrier

0.65

 TRAVEL

0.64

Travel

0.62

 Travel

0.61

TRAVEL

0.61

Activations Density 0.094%

terms related to travel and trips

No Comments

No Known Activations