INDEX

Explanations

phrases and details related to timing and sequence of events in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 annually

-0.52

 yearly

-0.52

 veckor

-0.46

每年

-0.46

 year

-0.46

Yearly

-0.43

 pekan

-0.43

yearly

-0.43

Week

-0.42

每月

-0.42

POSITIVE LOGITS

 propOrder

0.60

 minutes

0.55

 Minuten

0.50

 минут

0.50

minutes

0.49

 MessageBoxIcon

0.49

 minute

0.49

 hour

0.48

mapStateToProps

0.47

 minuter

0.47

Activations Density 0.840%

phrases and details related to timing and sequence of events in narratives

No Comments

No Known Activations