INDEX

Explanations

specific formatting elements or escape sequences in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

<em>

-0.58

</strong>

-0.54

 precisione

-0.51

lieben

-0.51

 bizony

-0.50

,\

-0.50

 rápidas

-0.50

er

-0.49

 adaptées

-0.48

,"

-0.47

POSITIVE LOGITS

1.31

 itſelf

1.04

✨:

1.03

 myſelf

0.90

Eſ

0.87

 становника

0.86

 kasarigan

0.86

 becauſe

0.85

 ſeveral

0.84

 himſelf

0.84

Activations Density 0.023%

specific formatting elements or escape sequences in the text

No Comments

No Known Activations