INDEX

Explanations

proper nouns, particularly names of people and places

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

 снимка

-0.66

SerialNumber

-0.63

 πρω

-0.63

Pter

-0.63

 Pall

-0.63

 ProductService

-0.62

 Juga

-0.61

IContainer

-0.60

 Völker

-0.59

 Galloway

-0.59

POSITIVE LOGITS

mias

0.82

xbb

0.81

awtextra

0.80

 Schott

0.78

ništ

0.78

Hayden

0.77

 Emits

0.75

 Bellow

0.75

IVEREF

0.74

Scot

0.73

Activations Density 2.111%

proper nouns, particularly names of people and places

No Comments

No Known Activations