INDEX

Explanations

activity related to purchasing and shopping experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ValueStyle

-0.91

ChildScrollView

-0.65

extAlignment

-0.61

 Showing

-0.56

Portale

-0.56

DJANGO

-0.55

showing

-0.55

versiti

-0.54

rical

-0.53

rativa

-0.53

POSITIVE LOGITS

 purchased

1.20

 purchase

1.20

 bought

1.16

 purchases

1.02

purchased

1.01

purchase

1.01

 membeli

0.98

 purchasing

0.97

 buying

0.95

bought

0.94

Activations Density 0.228%

activity related to purchasing and shopping experiences

No Comments

No Known Activations