INDEX

Explanations

words indicating changes in levels, particularly increases and decreases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

-0.57

άσ

-0.55

actéristique

-0.55

 half

-0.54

šanai

-0.54

danh

-0.52

ersdorf

-0.51

 Terre

-0.51

POSITIVE LOGITS

↑

5.00

↑

2.14

↑↑

1.55

↑↑↑

1.36

↓

1.32

↓

1.15

uparrow

0.97

migrationBuilder

0.96

 AssemblyTitle

0.94

ंदीखरीदारी

0.93

Activations Density 0.056%

words indicating changes in levels, particularly increases and decreases

No Comments

No Known Activations