INDEX

Explanations

references to months in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

Swa

-0.70

isticated

-0.68

 trúc

-0.67

 resultMap

-0.65

(',')

-0.65

''

-0.64

agra

-0.63

アリ

-0.62

 wieś

-0.61

-0.60

POSITIVE LOGITS

 month

1.81

 Month

1.71

month

1.53

 MONTH

1.53

MONTH

1.47

 months

1.39

 Months

1.35

Month

1.33

months

1.28

 monthly

1.24

Activations Density 0.058%

references to months in various contexts

No Comments

No Known Activations