INDEX

Explanations

words indicating progress or completion of tasks

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

Preceding abstract nouns or verbs

np_acts-logits-general · gemini-2.0-flash

defining or describing states

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

//

-0.55

 pourtant

-0.49

 gentes

-0.46

pires

-0.46

forRoot

-0.46

 onFailure

-0.45

 Quoi

-0.44

Till

-0.44

ابراین

-0.43

abetes

-0.43

POSITIVE LOGITS

FieldNumber

0.62

protoimpl

0.60

 незавершена

0.60

AddTagHelper

0.60

 Infórmanos

0.59

InjectAttribute

0.58

abestanden

0.58

 saying

0.56

 Exactos

0.55

Chham

0.55

Activations Density 0.444%

words indicating progress or completion of tasks

Preceding abstract nouns or verbs

defining or describing states

No Comments

No Known Activations