INDEX

Explanations

mathematical expressions and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ControllerAdvice

-0.50

Blurb

-0.49

énario

-0.48

참고

-0.42

><

-0.42

GLOBALS

-0.42

ffins

-0.42

地上

-0.41

↵↵↵

-0.41

tä

-0.40

POSITIVE LOGITS

 Audiodateien

0.78

>=</

0.77

 OFDb

0.77

 stretchy

0.73

>−</

0.67

 мәкал

0.66

Autoritní

0.66

 ostavi

0.65

脚注の使い方

0.64

 fence

0.64

Activations Density 0.147%

mathematical expressions and symbols

No Comments

No Known Activations