INDEX

Explanations

evidence of emotions and expressions in interactions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 tiện

-0.55

ัติ

-0.52

wpi

-0.52

 ilimit

-0.51

abatic

-0.51

livan

-0.51

olusi

-0.49

ⓘ

-0.49

SuccessListener

-0.49

 rêver

-0.48

POSITIVE LOGITS

idać

0.90

styleType

0.76

 visibly

0.75

 noticeably

0.70

 claramente

0.69

 AssemblyVersion

0.68

 clearly

0.68

clearly

0.64

tanleria

0.63

 noticeable

0.62

Activations Density 0.300%

evidence of emotions and expressions in interactions

No Comments

No Known Activations