INDEX

Explanations

instances of the word "One"

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

"One" followed by a noun or description

np_acts-logits-general · gemini-2.0-flash

introducing a notable point

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 متعلقه

-0.58

MigrationBuilder

-0.54

 respectively

-0.51

dorff

-0.47

 ModelExpression

-0.47

ibrator

-0.46

AndroidJUnit

-0.46

DotNetBar

-0.46

agerie

-0.46

 للمعارف

-0.46

POSITIVE LOGITS

 interesting

1.01

 thing

1.01

 reason

0.99

 important

0.92

 voordeel

0.91

way

0.89

 advantage

0.88

key

0.88

 notable

0.87

 benefit

0.87

Activations Density 0.225%

instances of the word "One"

"One" followed by a noun or description

introducing a notable point

No Comments

No Known Activations