INDEX

Explanations

words that mean "easy" or "difficult"

oai_token-act-pair · gemini-2.0-flash

easy

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TagMode

-0.94

 HasFactory

-0.73

 transfieras

-0.73

mybatisplus

-0.70

 traditionnels

-0.69

IntoConstraints

-0.65

+#+

-0.65

GEBURTSDATUM

-0.64

 militaires

-0.63

 Савезне

-0.63

POSITIVE LOGITS

 easily

1.34

 easy

1.30

 Easily

1.27

easily

1.26

 Easy

1.14

easy

1.14

Easily

1.10

Easy

1.08

 EASY

1.07

 easier

1.05

Activations Density 0.912%

words that mean "easy" or "difficult"

easy

No Comments

No Known Activations