INDEX

Explanations

references to time, specifically months

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

JEE

-0.68

''

-0.68

 resultMap

-0.65

agra

-0.63

\)

-0.62

isticated

-0.62

lidene

-0.62

writel

-0.61

(',')

-0.61

 trúc

-0.60

POSITIVE LOGITS

 month

3.18

 Month

2.87

month

2.67

 MONTH

2.63

Month

2.43

MONTH

2.31

 months

2.19

 Months

2.09

 monthly

1.94

months

1.91

Activations Density 0.043%

references to time, specifically months

No Comments

No Known Activations