INDEX

Explanations

specific years and related historical events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Anſ

-0.54

 faſt

-0.50

 Inſ

-0.49

 pleaſure

-0.48

 raiſ

-0.47

 ſta

-0.47

 juſt

-0.47

 cauſe

-0.47

 neceſſ

-0.46

 ſche

-0.46

POSITIVE LOGITS

forName

0.56

 mwaka

0.48

 years

0.48

 YEAR

0.47

gettimeofday

0.46

 year

0.46

 duração

0.46

 Jahre

0.45

DIPSETTING

0.45

easeOut

0.45

Activations Density 0.192%

specific years and related historical events

No Comments

No Known Activations