INDEX

Explanations

proper nouns, particularly names and locations related to historical events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

טו

-0.52

eraard

-0.48

upra

-0.47

此处

-0.46

 Hanley

-0.45

 corret

-0.44

 Dempsey

-0.44

Memoria

-0.42

GRE

-0.42

 دستی

-0.42

POSITIVE LOGITS

 تضيفلها

1.02

AddTagHelper

0.85

DoubleQuotes

0.81

VersionUID

0.80

0.75

aarrggbb

0.75

 мәкал

0.75

complexContent

0.74

πισ

0.70

 виправивши

0.69

Activations Density 2.963%

proper nouns, particularly names and locations related to historical events

No Comments

No Known Activations