INDEX

Explanations

questions about processes and their implications

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

phrases related to understanding and explaining reasons or methods.

oai_token-act-pair · gpt-4o Triggered by @timna

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Hentet

-0.73

stär

-0.50

บัติ

-0.50

mybatisplus

-0.50

otype

-0.48

期刊论文

-0.48

ndal

-0.48

eighth

-0.48

 manhã

-0.47

rachtet

-0.47

POSITIVE LOGITS

 therefor

0.99

 thereof

0.96

それを

0.85

 therefrom

0.81

それに

0.79

 daarvan

0.78

 therein

0.78

 thereupon

0.74

SequentialGroup

0.74

 thereon

0.72

Activations Density 0.504%

questions about processes and their implications

phrases related to understanding and explaining reasons or methods.

No Comments

No Known Activations