INDEX

Explanations

HTML tags and their attributes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Roskov

-1.11

ConstraintMaker

-1.05

 kasarigan

-1.05

Personendaten

-1.03

StoryboardSegue

-1.03

 Paglinawan

-1.02

تقاوى

-0.95

новниш

-0.94

 estekak

-0.93

 betweenstory

-0.90

POSITIVE LOGITS

ecm

0.55

orney

0.47

World

0.47

ia

0.46

 tali

0.45

žd

0.45

 World

0.43

0.41

ADORA

0.41

Activations Density 0.021%

HTML tags and their attributes

No Comments

No Known Activations