INDEX

Explanations

phrases indicating uncertainty or inquiry

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

oredCriteria

-0.75

 EnglishChoose

-0.64

databind

-0.64

暂无

-0.61



-0.60

ppincott

-0.60

PREFERRED

-0.60

QRST

-0.58

 devriez

-0.58

 تضيفلها

-0.58

POSITIVE LOGITS

 learns

0.92

 узнать

0.91

 learn

0.87

 узна

0.85

 know

0.83

 learnt

0.83

learn

0.82

 afla

0.82

Learn

0.77

 learned

0.77

Activations Density 0.124%

phrases indicating uncertainty or inquiry

No Comments

No Known Activations