INDEX

Explanations

references to shopping experiences and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 kasarigan

-0.83

fvar

-0.64

 saites

-0.62

 Seth

-0.61

Bhd

-0.58

Seth

-0.57

 initComponents

-0.57

protoimpl

-0.57

 NSCoder

-0.57

سطس

-0.56

POSITIVE LOGITS

 shopping

1.91

 Shopping

1.85

Shopping

1.81

 SHOPPING

1.79

shopping

1.71

 shoppers

1.49

 shopper

1.42

 grocery

1.20

购物

1.08

Grocery

1.08

Activations Density 0.044%

references to shopping experiences and places

No Comments

No Known Activations