INDEX

Explanations

commands or phrases indicating initiation or beginning actions

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

 שוליים

-0.75

 actualité

-0.70

Errorf

-0.68

 contentType

-0.66

tiker

-0.66

 Waray

-0.65

 Professions

-0.63

بوابة

-0.63

 numberWith

-0.62

POSITIVE LOGITS

 start

2.21

 started

2.03

 starts

1.99

 starting

1.86

 Start

1.82

 Starts

1.71

 begin

1.68

 START

1.63

 Started

1.61

started

1.60

Activations Density 0.103%

commands or phrases indicating initiation or beginning actions

No Comments

No Known Activations