INDEX

Explanations

numeric values and percentages, indicating statistical data or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

-0.74

Cor

-0.66

↵↵

-0.62

<eos>

-0.62

-0.61

 за

-0.60

...

-0.59

 Krueger

-0.58

↵

-0.58

Tr

-0.56

POSITIVE LOGITS

Datuak

1.46

 myſelf

1.21

 doubtnut

1.06

 Majefty

1.04

 kaynağından

1.03

 feroit

1.03

 виправивши

1.03

 Monfieur

1.01

 Maren

1.01

 himſelf

0.99

Activations Density 0.858%

numeric values and percentages, indicating statistical data or measurements

No Comments

No Known Activations