INDEX

Explanations

sections or cues indicating a continuation or a transition in text

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

Code, names, and programming-related terms

np_acts-logits-general · gemini-2.0-flash

technical terms and labels

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

ile

-0.45

tom

-0.45

ces

-0.42

ony

-0.41

ary

-0.41

val

-0.41

ry

-0.40

vers

-0.40

er

-0.40

cing

-0.39

POSITIVE LOGITS

LabelTagHelper

0.83

 ModelExpression

0.83

 TestBed

0.82

 wireType

0.80

 ویکی‌پدیا

0.78

 CommonModule

0.75

 '\\;'

0.74

Personendaten

0.74

GEBURTS

0.72

ArgsConstructor

0.72

Activations Density 0.069%

sections or cues indicating a continuation or a transition in text

Code, names, and programming-related terms

technical terms and labels

No Comments

No Known Activations