INDEX

Explanations

evidence of statistical significance in experimental results

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

Diagram annotations: arrows, lines, symbols, and dots

np_acts-logits-general · gemini-2.0-flash

dashed, dotted, and arrows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

ViewImports

-0.67

OGND

-0.55

ChildScrollView

-0.55

 XCTest

-0.55

WriteTagHelper

-0.51

 WebDriverWait

-0.51

GOTREF

-0.47

NUMX

-0.46

؜

-0.44

MENAFN

-0.43

POSITIVE LOGITS

 arrows

1.29

 dashed

1.09

 dotted

1.08

 arrow

1.05

arrows

0.95

 circled

0.91

dashed

0.88

 Arrows

0.88

dotted

0.86

 flechas

0.86

Activations Density 1.702%

evidence of statistical significance in experimental results

Diagram annotations: arrows, lines, symbols, and dots

dashed, dotted, and arrows

No Comments

No Known Activations