INDEX

Explanations

punctuation and symbols indicating transitions or changes in thought

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

[]

-0.59

}{*}{

-0.55

CloseOperation

-0.55

 honom

-0.54

him

-0.54

usic

-0.53

 المعيارى

-0.53

standig

-0.53

اتی

-0.53

textsc

-0.52

POSITIVE LOGITS

verwijspagina

1.03

 disambiguazione

0.84

 mxArray

0.83

awtextra

0.80

__':

0.80

 pinulongan

0.80

 including

0.76

because

0.75

Capítulo

0.74

perhaps

0.74

Activations Density 0.211%

punctuation and symbols indicating transitions or changes in thought

No Comments

No Known Activations