INDEX

Explanations

references to legal or regulatory content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

➯

-0.69

 stället

-0.68

 >=",

-0.68

RTLD

-0.66

ViewFeatures

-0.64

cticut

-0.63

Citiți

-0.62

PreferredItem

-0.61

GMENT

-0.61

TagMode

-0.60

POSITIVE LOGITS

 فريبيس

0.56

WebVitals

0.54

Jereo

0.52

 الرياضيه

0.52

DotNetBar

0.51

jstor

0.51

<bos>

0.50

 nahilalakip

0.47

تقاوى

0.46

principalColumn

0.45

Activations Density 0.432%

references to legal or regulatory content

No Comments

No Known Activations