INDEX

Explanations

keywords related to time and temporal phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

-0.62

 Drapeau

-0.59

 متعلقه

-0.54

 للاسماء

-0.54

ंदीखरीदारी

-0.52

Autoritní

-0.51

 Chất

-0.49

 Inhibitors

-0.49

IntoConstraints

-0.49

 محفوظة

-0.49

POSITIVE LOGITS

Day

1.12

 Time

1.03

 Evening

1.01

 Night

1.00

 Morning

0.97

Day

0.94

 Weekend

0.92

 Week

0.91

 Afternoon

0.87

Night

0.85

Activations Density 0.550%

keywords related to time and temporal phrases

No Comments

No Known Activations