INDEX

Explanations

indicators of changes or variations in data or parameters in a scientific context

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

Děkuji

-0.61

mybatisplus

-0.59

actéristique

-0.55

 itſelf

-0.53

 iſt

-0.52

Efq

-0.52

aterial

-0.51

šanai

-0.51

ffilm

-0.51

άσ

-0.51

POSITIVE LOGITS

↑

5.36

↑

2.17

↑↑

1.50

↓

1.33

↑↑↑

1.30

↓

1.06

1.02

uparrow

0.98

⇑

0.97

 الحره

0.88

Activations Density 0.063%

indicators of changes or variations in data or parameters in a scientific context

No Comments

No Known Activations