INDEX

Explanations

the variety of uses and contexts of the word "to."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

RegistryLite

-0.52

emde

-0.51

 Administrativna

-0.50

vericks

-0.49

uari

-0.48

ấu

-0.48

 &___

-0.48

INCREF

-0.48

seende

-0.48

يكب

-0.48

POSITIVE LOGITS

 htons

0.65

 المعيارى

0.62

 houſe

0.61

 utafitiHapana

0.60

 purpoſe

0.60

astify

0.59

 Anſ

0.59

 pleaſure

0.59

 greateſt

0.58

 myſelf

0.57

Activations Density 0.173%

the variety of uses and contexts of the word "to."

No Comments

No Known Activations