INDEX

Explanations

references to specific months and weeks in time

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-0.85

 للاسماء

-0.72

''

-0.70

(',')

-0.66

 resultMap

-0.63

writel

-0.63

CURS

-0.63

κτηρισ

-0.62

róleo

-0.61

 HANS

-0.61

POSITIVE LOGITS

 month

3.12

 Month

2.75

 MONTH

2.56

month

2.50

Month

2.34

MONTH

2.08

 monthly

1.94

 Monat

1.78

 Monthly

1.76

 week

1.75

Activations Density 0.071%

references to specific months and weeks in time

No Comments

No Known Activations