INDEX

Explanations

proper nouns and names associated with individuals

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

 MainAxisSize

-0.57

CodedInputStream

-0.55

KeyName

-0.52

windowFixed

-0.49

 Seeder

-0.48

País

-0.47

 komp

-0.47

 IBOutlet

-0.47

 متحده

-0.47

irão

-0.45

POSITIVE LOGITS

 ***!

0.70

 الرياضيه

0.69

]._

0.69

 juſ

0.68

 ſche

0.66

 pleaſure

0.64

 faſt

0.64

 myſelf

0.63

 tramontina

0.62

ſelf

0.61

Activations Density 0.333%

proper nouns and names associated with individuals

No Comments

No Known Activations