INDEX

Explanations

words expressing positive outcomes or serendipitous situations

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

 problems

-0.54

 questions

-0.50

 خواه

-0.47

fz

-0.47

Nye

-0.47

Enders

-0.47

gette

-0.46

 viewType

-0.46

èches

-0.45

fisk

-0.44

POSITIVE LOGITS

 fortunately

2.48

 luckily

2.42

Fortunately

2.26

Luckily

2.25

 Fortunately

2.19

 Luckily

2.17

 thankfully

2.14

 lucky

2.12

 fortunate

2.11

Thankfully

2.03

Activations Density 0.123%

words expressing positive outcomes or serendipitous situations

No Comments

No Known Activations