INDEX

Explanations

occurrences of the prefix "un-" in various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

styleType

-0.73

uage

-0.66

 betweenstory

-0.64

seater

-0.61

 pinulongan

-0.60

 IService

-0.59

Trayectoria

-0.59

gway

-0.58

ydd

-0.58

VideoCapture

-0.58

POSITIVE LOGITS

un

3.48

UN

2.60

Un

1.98

uns

1.92

Un

1.63

un

1.59

ún

1.51

une

1.50

unse

1.44

UN

1.44

Activations Density 0.068%

occurrences of the prefix "un-" in various forms

No Comments

No Known Activations