INDEX

Explanations

specific numeric values or structured data elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

lgari

-0.64

WebElementEntity

-0.61

 SUDOC

-0.56

 Offisielt

-0.56

줌

-0.56

Espèce

-0.55

ázquez

-0.55

 Çünkü

-0.55

Достоинства

-0.52

ulite

-0.51

POSITIVE LOGITS

how

1.41

How

1.27

 what

1.26

How

1.21

 What

1.18

What

1.15

why

1.11

how

1.08

what

1.05

Why

0.97

Activations Density 0.266%

specific numeric values or structured data elements

No Comments

No Known Activations