INDEX

Explanations

comparative phrases indicating relative differences in magnitude or quantity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

皮

-0.47

-0.43

вич

-0.43

je

-0.43

–

-0.42

jed

-0.41

起

-0.41

Per

-0.41

 […]

-0.40

cored

-0.40

POSITIVE LOGITS

 MainAxisSize

1.12

 OFDb

1.00

zzleHttp

0.98

contentLoaded

0.95

ConstraintMaker

0.93

 NSCoder

0.92

InjectAttribute

0.88

 myſelf

0.87

 تضيفلها

0.86

DockStyle

0.86

Activations Density 0.429%

comparative phrases indicating relative differences in magnitude or quantity

No Comments

No Known Activations