INDEX

Explanations

phrases indicating varying degrees of extent or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

postValue

-0.53

MethodManager

-0.50

ьа

-0.50

pě

-0.49

 Nadel

-0.49

 standard

-0.49

intz

-0.48

 sticking

-0.48

 stick

-0.48

createNewFile

-0.48

POSITIVE LOGITS

 Extent

1.12

 extent

0.92

WriteTagHelper

0.86

extent

0.81

]--;

0.81

Personensuche

0.77

 ways

0.77

 AssemblyTitle

0.77

onAttach

0.75

 contextLoads

0.73

Activations Density 0.199%

phrases indicating varying degrees of extent or significance

No Comments

No Known Activations